Add Mask2Former (#20792)

* Adds Mask2Former to transformers Co-authored-by: Shivalika Singh <shivalikasingh95@gmail.com> Co-authored-by: Shivalika Singh <73357305+shivalikasingh95@users.noreply.github.com> Co-authored-by: NielsRogge <48327001+NielsRogge@users.noreply.github.com> Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>

Add Mask2Former (#20792)
* Adds Mask2Former to transformers Co-authored-by: Shivalika Singh <shivalikasingh95@gmail.com> Co-authored-by: Shivalika Singh <73357305+shivalikasingh95@users.noreply.github.com> Co-authored-by: NielsRogge <48327001+NielsRogge@users.noreply.github.com> Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>
2411f0e4 · Alara Dirik · GitHub · 9edf3758 · 2411f0e4 · 2411f0e4
Unverified Commit 2411f0e4 authored Jan 16, 2023 by Alara Dirik Committed by GitHub Jan 16, 2023
20 changed files
--- a/README.md
+++ b/README.md
@@ -346,6 +346,7 @@ Current number of checkpoints: ![](https://img.shields.io/endpoint?url=https://h
 1. **[M2M100](https://huggingface.co/docs/transformers/model_doc/m2m_100)** (from Facebook) released with the paper [Beyond English-Centric Multilingual Machine Translation](https://arxiv.org/abs/2010.11125) by Angela Fan, Shruti Bhosale, Holger Schwenk, Zhiyi Ma, Ahmed El-Kishky, Siddharth Goyal, Mandeep Baines, Onur Celebi, Guillaume Wenzek, Vishrav Chaudhary, Naman Goyal, Tom Birch, Vitaliy Liptchinsky, Sergey Edunov, Edouard Grave, Michael Auli, Armand Joulin.
 1. **[MarianMT](https://huggingface.co/docs/transformers/model_doc/marian)** Machine translation models trained using [OPUS](http://opus.nlpl.eu/) data by Jörg Tiedemann. The [Marian Framework](https://marian-nmt.github.io/) is being developed by the Microsoft Translator Team.
 1. **[MarkupLM](https://huggingface.co/docs/transformers/model_doc/markuplm)** (from Microsoft Research Asia) released with the paper [MarkupLM: Pre-training of Text and Markup Language for Visually-rich Document Understanding](https://arxiv.org/abs/2110.08518) by Junlong Li, Yiheng Xu, Lei Cui, Furu Wei.
+1. **[Mask2Former](https://huggingface.co/docs/transformers/main/model_doc/mask2former)** (from FAIR and UIUC) released with the paper [Masked-attention Mask Transformer for Universal Image Segmentation](https://arxiv.org/abs/2112.01527) by Bowen Cheng, Ishan Misra, Alexander G. Schwing, Alexander Kirillov, Rohit Girdhar.
 1. **[MaskFormer](https://huggingface.co/docs/transformers/model_doc/maskformer)** (from Meta and UIUC) released with the paper [Per-Pixel Classification is Not All You Need for Semantic Segmentation](https://arxiv.org/abs/2107.06278) by Bowen Cheng, Alexander G. Schwing, Alexander Kirillov.
 1. **[mBART](https://huggingface.co/docs/transformers/model_doc/mbart)** (from Facebook) released with the paper [Multilingual Denoising Pre-training for Neural Machine Translation](https://arxiv.org/abs/2001.08210) by Yinhan Liu, Jiatao Gu, Naman Goyal, Xian Li, Sergey Edunov, Marjan Ghazvininejad, Mike Lewis, Luke Zettlemoyer.
 1. **[mBART-50](https://huggingface.co/docs/transformers/model_doc/mbart)** (from Facebook) released with the paper [Multilingual Translation with Extensible Multilingual Pretraining and Finetuning](https://arxiv.org/abs/2008.00401) by Yuqing Tang, Chau Tran, Xian Li, Peng-Jen Chen, Naman Goyal, Vishrav Chaudhary, Jiatao Gu, Angela Fan.

--- a/README_es.md
+++ b/README_es.md
@@ -346,6 +346,7 @@ Número actual de puntos de control: ![](https://img.shields.io/endpoint?url=htt
 1. **[M2M100](https://huggingface.co/docs/transformers/model_doc/m2m_100)** (from Facebook) released with the paper [Beyond English-Centric Multilingual Machine Translation](https://arxiv.org/abs/2010.11125) by Angela Fan, Shruti Bhosale, Holger Schwenk, Zhiyi Ma, Ahmed El-Kishky, Siddharth Goyal, Mandeep Baines, Onur Celebi, Guillaume Wenzek, Vishrav Chaudhary, Naman Goyal, Tom Birch, Vitaliy Liptchinsky, Sergey Edunov, Edouard Grave, Michael Auli, Armand Joulin.
 1. **[MarianMT](https://huggingface.co/docs/transformers/model_doc/marian)** Machine translation models trained using [OPUS](http://opus.nlpl.eu/) data by Jörg Tiedemann. The [Marian Framework](https://marian-nmt.github.io/) is being developed by the Microsoft Translator Team.
 1. **[MarkupLM](https://huggingface.co/docs/transformers/model_doc/markuplm)** (from Microsoft Research Asia) released with the paper [MarkupLM: Pre-training of Text and Markup Language for Visually-rich Document Understanding](https://arxiv.org/abs/2110.08518) by Junlong Li, Yiheng Xu, Lei Cui, Furu Wei.
+1. **[Mask2Former](https://huggingface.co/docs/transformers/main/model_doc/mask2former)** (from FAIR and UIUC) released with the paper [Masked-attention Mask Transformer for Universal Image Segmentation](https://arxiv.org/abs/2112.01527) by Bowen Cheng, Ishan Misra, Alexander G. Schwing, Alexander Kirillov, Rohit Girdhar.
 1. **[MaskFormer](https://huggingface.co/docs/transformers/model_doc/maskformer)** (from Meta and UIUC) released with the paper [Per-Pixel Classification is Not All You Need for Semantic Segmentation](https://arxiv.org/abs/2107.06278) by Bowen Cheng, Alexander G. Schwing, Alexander Kirillov.
 1. **[mBART](https://huggingface.co/docs/transformers/model_doc/mbart)** (from Facebook) released with the paper [Multilingual Denoising Pre-training for Neural Machine Translation](https://arxiv.org/abs/2001.08210) by Yinhan Liu, Jiatao Gu, Naman Goyal, Xian Li, Sergey Edunov, Marjan Ghazvininejad, Mike Lewis, Luke Zettlemoyer.
 1. **[mBART-50](https://huggingface.co/docs/transformers/model_doc/mbart)** (from Facebook) released with the paper [Multilingual Translation with Extensible Multilingual Pretraining and Finetuning](https://arxiv.org/abs/2008.00401) by Yuqing Tang, Chau Tran, Xian Li, Peng-Jen Chen, Naman Goyal, Vishrav Chaudhary, Jiatao Gu, Angela Fan.

--- a/README_hd.md
+++ b/README_hd.md
@@ -319,6 +319,7 @@ conda install -c huggingface transformers
 1. **[M2M100](https://huggingface.co/docs/transformers/model_doc/m2m_100)** (फेसबुक से) साथ देने वाला पेपर [बियॉन्ड इंग्लिश-सेंट्रिक मल्टीलिंगुअल मशीन ट्रांसलेशन](https://arxiv.org/ एब्स/2010.11125) एंजेला फैन, श्रुति भोसले, होल्गर श्वेन्क, झी मा, अहमद अल-किश्की, सिद्धार्थ गोयल, मनदीप बैनेस, ओनूर सेलेबी, गुइल्लाम वेन्जेक, विश्रव चौधरी, नमन गोयल, टॉम बर्च, विटाली लिपचिंस्की, सर्गेई एडुनोव, एडौर्ड द्वारा ग्रेव, माइकल औली, आर्मंड जौलिन द्वारा पोस्ट किया गया।
 1. **[MarianMT](https://huggingface.co/docs/transformers/model_doc/marian)** Jörg द्वारा [OPUS](http://opus.nlpl.eu/) डेटा से प्रशिक्षित मशीनी अनुवाद मॉडल पोस्ट किया गया टाइडेमैन द्वारा। [मैरियन फ्रेमवर्क](https://marian-nmt.github.io/) माइक्रोसॉफ्ट ट्रांसलेटर टीम द्वारा विकसित।
 1. **[MarkupLM](https://huggingface.co/docs/transformers/model_doc/markuplm)** (माइक्रोसॉफ्ट रिसर्च एशिया से) साथ में पेपर [मार्कअपएलएम: विजुअली-रिच डॉक्यूमेंट अंडरस्टैंडिंग के लिए टेक्स्ट और मार्कअप लैंग्वेज का प्री-ट्रेनिंग] (https://arxiv.org/abs/2110.08518) जुनलॉन्ग ली, यिहेंग जू, लेई कुई, फुरु द्वारा वी द्वारा पोस्ट किया गया।
+1. **[Mask2Former](https://huggingface.co/docs/transformers/main/model_doc/mask2former)** (FAIR and UIUC से) Bowen Cheng, Ishan Misra, Alexander G. Schwing, Alexander Kirillov, Rohit Girdhar. द्वाराअनुसंधान पत्र [Masked-attention Mask Transformer for Universal Image Segmentation](https://arxiv.org/abs/2112.01527) के साथ जारी किया गया
 1. **[MaskFormer](https://huggingface.co/docs/transformers/model_doc/maskformer)** (मेटा और UIUC से) पेपर के साथ जारी किया गया [प्रति-पिक्सेल वर्गीकरण वह सब नहीं है जिसकी आपको सिमेंटिक सेगमेंटेशन की आवश्यकता है] (https://arxiv.org/abs/2107.06278) बोवेन चेंग, अलेक्जेंडर जी. श्विंग, अलेक्जेंडर किरिलोव द्वारा >>>>>> रिबेस ठीक करें
 1. **[mBART](https://huggingface.co/docs/transformers/model_doc/mbart)** (फेसबुक से) साथ में पेपर [न्यूरल मशीन ट्रांसलेशन के लिए मल्टीलिंगुअल डीनोइजिंग प्री-ट्रेनिंग](https://arxiv. org/abs/2001.08210) यिनहान लियू, जियाताओ गु, नमन गोयल, जियान ली, सर्गेई एडुनोव, मार्जन ग़ज़विनिनेजाद, माइक लुईस, ल्यूक ज़ेटलमॉयर द्वारा।
 1. **[mBART-50](https://huggingface.co/docs/transformers/model_doc/mbart)** (फेसबुक से) साथ में पेपर [एक्स्टेंसिबल बहुभाषी प्रीट्रेनिंग और फाइनट्यूनिंग के साथ बहुभाषी अनुवाद](https://arxiv युकिंग टैंग, चाउ ट्रान, जियान ली, पेंग-जेन चेन, नमन गोयल, विश्रव चौधरी, जियाताओ गु, एंजेला फैन द्वारा .org/abs/2008.00401)।

--- a/README_ja.md
+++ b/README_ja.md
@@ -381,6 +381,7 @@ Flax、PyTorch、TensorFlowをcondaでインストールする方法は、それ
 1. **[M2M100](https://huggingface.co/docs/transformers/model_doc/m2m_100)** (Facebook から) Angela Fan, Shruti Bhosale, Holger Schwenk, Zhiyi Ma, Ahmed El-Kishky, Siddharth Goyal, Mandeep Baines, Onur Celebi, Guillaume Wenzek, Vishrav Chaudhary, Naman Goyal, Tom Birch, Vitaliy Liptchinsky, Sergey Edunov, Edouard Grave, Michael Auli, Armand Joulin から公開された研究論文: [Beyond English-Centric Multilingual Machine Translation](https://arxiv.org/abs/2010.11125)
 1. **[MarianMT](https://huggingface.co/docs/transformers/model_doc/marian)** Jörg Tiedemann から. [OPUS](http://opus.nlpl.eu/) を使いながら学習された "Machine translation" (マシントランスレーション) モデル. [Marian Framework](https://marian-nmt.github.io/) はMicrosoft Translator Team　が現在開発中です.
 1. **[MarkupLM](https://huggingface.co/docs/transformers/model_doc/markuplm)** (Microsoft Research Asia から) Junlong Li, Yiheng Xu, Lei Cui, Furu Wei から公開された研究論文: [MarkupLM: Pre-training of Text and Markup Language for Visually-rich Document Understanding](https://arxiv.org/abs/2110.08518)
+1. **[Mask2Former](https://huggingface.co/docs/transformers/main/model_doc/mask2former)** (FAIR and UIUC から) Bowen Cheng, Ishan Misra, Alexander G. Schwing, Alexander Kirillov, Rohit Girdhar. から公開された研究論文 [Masked-attention Mask Transformer for Universal Image Segmentation](https://arxiv.org/abs/2112.01527)
 1. **[MaskFormer](https://huggingface.co/docs/transformers/model_doc/maskformer)** (Meta and UIUC から) Bowen Cheng, Alexander G. Schwing, Alexander Kirillov から公開された研究論文: [Per-Pixel Classification is Not All You Need for Semantic Segmentation](https://arxiv.org/abs/2107.06278)
 1. **[mBART](https://huggingface.co/docs/transformers/model_doc/mbart)** (Facebook から) Yinhan Liu, Jiatao Gu, Naman Goyal, Xian Li, Sergey Edunov, Marjan Ghazvininejad, Mike Lewis, Luke Zettlemoyer から公開された研究論文: [Multilingual Denoising Pre-training for Neural Machine Translation](https://arxiv.org/abs/2001.08210)
 1. **[mBART-50](https://huggingface.co/docs/transformers/model_doc/mbart)** (Facebook から) Yuqing Tang, Chau Tran, Xian Li, Peng-Jen Chen, Naman Goyal, Vishrav Chaudhary, Jiatao Gu, Angela Fan から公開された研究論文: [Multilingual Translation with Extensible Multilingual Pretraining and Finetuning](https://arxiv.org/abs/2008.00401)

--- a/README_ko.md
+++ b/README_ko.md
@@ -296,6 +296,7 @@ Flax, PyTorch, TensorFlow 설치 페이지에서 이들을 conda로 설치하는
 1. **[M2M100](https://huggingface.co/docs/transformers/model_doc/m2m_100)** (Facebook 에서) Angela Fan, Shruti Bhosale, Holger Schwenk, Zhiyi Ma, Ahmed El-Kishky, Siddharth Goyal, Mandeep Baines, Onur Celebi, Guillaume Wenzek, Vishrav Chaudhary, Naman Goyal, Tom Birch, Vitaliy Liptchinsky, Sergey Edunov, Edouard Grave, Michael Auli, Armand Joulin 의 [Beyond English-Centric Multilingual Machine Translation](https://arxiv.org/abs/2010.11125) 논문과 함께 발표했습니다.
 1. **[MarianMT](https://huggingface.co/docs/transformers/model_doc/marian)** Machine translation models trained using [OPUS](http://opus.nlpl.eu/) data by Jörg Tiedemann. The [Marian Framework](https://marian-nmt.github.io/) is being developed by the Microsoft Translator Team.
 1. **[MarkupLM](https://huggingface.co/docs/transformers/model_doc/markuplm)** (Microsoft Research Asia 에서) Junlong Li, Yiheng Xu, Lei Cui, Furu Wei 의 [MarkupLM: Pre-training of Text and Markup Language for Visually-rich Document Understanding](https://arxiv.org/abs/2110.08518) 논문과 함께 발표했습니다.
+1. **[Mask2Former](https://huggingface.co/docs/transformers/main/model_doc/mask2former)** (FAIR and UIUC 에서 제공)은 Bowen Cheng, Ishan Misra, Alexander G. Schwing, Alexander Kirillov, Rohit Girdhar.의 [Masked-attention Mask Transformer for Universal Image Segmentation](https://arxiv.org/abs/2112.01527)논문과 함께 발표했습니다.
 1. **[MaskFormer](https://huggingface.co/docs/transformers/model_doc/maskformer)** (Meta and UIUC 에서) Bowen Cheng, Alexander G. Schwing, Alexander Kirillov 의 [Per-Pixel Classification is Not All You Need for Semantic Segmentation](https://arxiv.org/abs/2107.06278) 논문과 함께 발표했습니다.
 1. **[mBART](https://huggingface.co/docs/transformers/model_doc/mbart)** (Facebook 에서) Yinhan Liu, Jiatao Gu, Naman Goyal, Xian Li, Sergey Edunov, Marjan Ghazvininejad, Mike Lewis, Luke Zettlemoyer 의 [Multilingual Denoising Pre-training for Neural Machine Translation](https://arxiv.org/abs/2001.08210) 논문과 함께 발표했습니다.
 1. **[mBART-50](https://huggingface.co/docs/transformers/model_doc/mbart)** (Facebook 에서) Yuqing Tang, Chau Tran, Xian Li, Peng-Jen Chen, Naman Goyal, Vishrav Chaudhary, Jiatao Gu, Angela Fan 의 [Multilingual Translation with Extensible Multilingual Pretraining and Finetuning](https://arxiv.org/abs/2008.00401) 논문과 함께 발표했습니다.

--- a/README_zh-hans.md
+++ b/README_zh-hans.md
@@ -320,6 +320,7 @@ conda install -c huggingface transformers
 1. **[M2M100](https://huggingface.co/docs/transformers/model_doc/m2m_100)** (来自 Facebook) 伴随论文 [Beyond English-Centric Multilingual Machine Translation](https://arxiv.org/abs/2010.11125) 由 Angela Fan, Shruti Bhosale, Holger Schwenk, Zhiyi Ma, Ahmed El-Kishky, Siddharth Goyal, Mandeep Baines, Onur Celebi, Guillaume Wenzek, Vishrav Chaudhary, Naman Goyal, Tom Birch, Vitaliy Liptchinsky, Sergey Edunov, Edouard Grave, Michael Auli, Armand Joulin 发布。
 1. **[MarianMT](https://huggingface.co/docs/transformers/model_doc/marian)** 用 [OPUS](http://opus.nlpl.eu/) 数据训练的机器翻译模型由 Jörg Tiedemann 发布。[Marian Framework](https://marian-nmt.github.io/) 由微软翻译团队开发。
 1. **[MarkupLM](https://huggingface.co/docs/transformers/model_doc/markuplm)** (来自 Microsoft Research Asia) 伴随论文 [MarkupLM: Pre-training of Text and Markup Language for Visually-rich Document Understanding](https://arxiv.org/abs/2110.08518) 由 Junlong Li, Yiheng Xu, Lei Cui, Furu Wei 发布。
+1. **[Mask2Former](https://huggingface.co/docs/transformers/main/model_doc/mask2former)** (来自 FAIR and UIUC) 伴随论文 [Masked-attention Mask Transformer for Universal Image Segmentation](https://arxiv.org/abs/2112.01527) 由 Bowen Cheng, Ishan Misra, Alexander G. Schwing, Alexander Kirillov, Rohit Girdhar 发布。
 1. **[MaskFormer](https://huggingface.co/docs/transformers/model_doc/maskformer)** (from Meta and UIUC) released with the paper [Per-Pixel Classification is Not All You Need for Semantic Segmentation](https://arxiv.org/abs/2107.06278) by Bowen Cheng, Alexander G. Schwing, Alexander Kirillov  >>>>>>> Fix rebase
 1. **[mBART](https://huggingface.co/docs/transformers/model_doc/mbart)** (来自 Facebook) 伴随论文 [Multilingual Denoising Pre-training for Neural Machine Translation](https://arxiv.org/abs/2001.08210) 由 Yinhan Liu, Jiatao Gu, Naman Goyal, Xian Li, Sergey Edunov, Marjan Ghazvininejad, Mike Lewis, Luke Zettlemoyer 发布。
 1. **[mBART-50](https://huggingface.co/docs/transformers/model_doc/mbart)** (来自 Facebook) 伴随论文 [Multilingual Translation with Extensible Multilingual Pretraining and Finetuning](https://arxiv.org/abs/2008.00401) 由 Yuqing Tang, Chau Tran, Xian Li, Peng-Jen Chen, Naman Goyal, Vishrav Chaudhary, Jiatao Gu, Angela Fan 发布。

--- a/README_zh-hant.md
+++ b/README_zh-hant.md
@@ -332,6 +332,7 @@ conda install -c huggingface transformers
 1. **[M2M100](https://huggingface.co/docs/transformers/model_doc/m2m_100)** (from Facebook) released with the paper [Beyond English-Centric Multilingual Machine Translation](https://arxiv.org/abs/2010.11125) by Angela Fan, Shruti Bhosale, Holger Schwenk, Zhiyi Ma, Ahmed El-Kishky, Siddharth Goyal, Mandeep Baines, Onur Celebi, Guillaume Wenzek, Vishrav Chaudhary, Naman Goyal, Tom Birch, Vitaliy Liptchinsky, Sergey Edunov, Edouard Grave, Michael Auli, Armand Joulin.
 1. **[MarianMT](https://huggingface.co/docs/transformers/model_doc/marian)** Machine translation models trained using [OPUS](http://opus.nlpl.eu/) data by Jörg Tiedemann. The [Marian Framework](https://marian-nmt.github.io/) is being developed by the Microsoft Translator Team.
 1. **[MarkupLM](https://huggingface.co/docs/transformers/model_doc/markuplm)** (from Microsoft Research Asia) released with the paper [MarkupLM: Pre-training of Text and Markup Language for Visually-rich Document Understanding](https://arxiv.org/abs/2110.08518) by Junlong Li, Yiheng Xu, Lei Cui, Furu Wei.
+1. **[Mask2Former](https://huggingface.co/docs/transformers/main/model_doc/mask2former)** (from FAIR and UIUC) released with the paper [Masked-attention Mask Transformer for Universal Image Segmentation](https://arxiv.org/abs/2112.01527) by Bowen Cheng, Ishan Misra, Alexander G. Schwing, Alexander Kirillov, Rohit Girdhar.
 1. **[MaskFormer](https://huggingface.co/docs/transformers/model_doc/maskformer)** (from Meta and UIUC) released with the paper [Per-Pixel Classification is Not All You Need for Semantic Segmentation](https://arxiv.org/abs/2107.06278) by Bowen Cheng, Alexander G. Schwing, Alexander Kirillov
 1. **[mBART](https://huggingface.co/docs/transformers/model_doc/mbart)** (from Facebook) released with the paper [Multilingual Denoising Pre-training for Neural Machine Translation](https://arxiv.org/abs/2001.08210) by Yinhan Liu, Jiatao Gu, Naman Goyal, Xian Li, Sergey Edunov, Marjan Ghazvininejad, Mike Lewis, Luke Zettlemoyer.
 1. **[mBART-50](https://huggingface.co/docs/transformers/model_doc/mbart)** (from Facebook) released with the paper [Multilingual Translation with Extensible Multilingual Pretraining and Finetuning](https://arxiv.org/abs/2008.00401) by Yuqing Tang, Chau Tran, Xian Li, Peng-Jen Chen, Naman Goyal, Vishrav Chaudhary, Jiatao Gu, Angela Fan.

--- a/docs/source/de/index.mdx
+++ b/docs/source/de/index.mdx
@@ -115,6 +115,7 @@ Die Bibliothek enthält derzeit JAX-, PyTorch- und TensorFlow-Implementierungen,
 1. **[M-CTC-T](model_doc/mctct)** (from Facebook) released with the paper [Pseudo-Labeling For Massively Multilingual Speech Recognition](https://arxiv.org/abs/2111.00161) by Loren Lugosch, Tatiana Likhomanenko, Gabriel Synnaeve, and Ronan Collobert.
 1. **[M2M100](model_doc/m2m_100)** (from Facebook) released with the paper [Beyond English-Centric Multilingual Machine Translation](https://arxiv.org/abs/2010.11125) by Angela Fan, Shruti Bhosale, Holger Schwenk, Zhiyi Ma, Ahmed El-Kishky, Siddharth Goyal, Mandeep Baines, Onur Celebi, Guillaume Wenzek, Vishrav Chaudhary, Naman Goyal, Tom Birch, Vitaliy Liptchinsky, Sergey Edunov, Edouard Grave, Michael Auli, Armand Joulin.
 1. **[MarianMT](model_doc/marian)** Machine translation models trained using [OPUS](http://opus.nlpl.eu/) data by Jörg Tiedemann. The [Marian Framework](https://marian-nmt.github.io/) is being developed by the Microsoft Translator Team.
+1. **[Mask2Former](model_doc/mask2former)** (from FAIR and UIUC) released with the paper [Masked-attention Mask Transformer for Universal Image Segmentation](https://arxiv.org/abs/2112.01527) by Bowen Cheng, Ishan Misra, Alexander G. Schwing, Alexander Kirillov, Rohit Girdhar.
 1. **[MaskFormer](model_doc/maskformer)** (from Meta and UIUC) released with the paper [Per-Pixel Classification is Not All You Need for Semantic Segmentation](https://arxiv.org/abs/2107.06278) by Bowen Cheng, Alexander G. Schwing, Alexander Kirillov.
 1. **[mBART](model_doc/mbart)** (from Facebook) released with the paper [Multilingual Denoising Pre-training for Neural Machine Translation](https://arxiv.org/abs/2001.08210) by Yinhan Liu, Jiatao Gu, Naman Goyal, Xian Li, Sergey Edunov, Marjan Ghazvininejad, Mike Lewis, Luke Zettlemoyer.
 1. **[mBART-50](model_doc/mbart)** (from Facebook) released with the paper [Multilingual Translation with Extensible Multilingual Pretraining and Finetuning](https://arxiv.org/abs/2008.00401) by Yuqing Tang, Chau Tran, Xian Li, Peng-Jen Chen, Naman Goyal, Vishrav Chaudhary, Jiatao Gu, Angela Fan.

--- a/docs/source/en/_toctree.yml
+++ b/docs/source/en/_toctree.yml
@@ -422,6 +422,8 @@
        title: ImageGPT
      - local: model_doc/levit
        title: LeViT
+      - local: model_doc/mask2former
+        title: Mask2Former
      - local: model_doc/maskformer
        title: MaskFormer
      - local: model_doc/mobilenet_v1

--- a/docs/source/en/index.mdx
+++ b/docs/source/en/index.mdx
@@ -133,6 +133,7 @@ The documentation is organized into five sections:
 1. **[M2M100](model_doc/m2m_100)** (from Facebook) released with the paper [Beyond English-Centric Multilingual Machine Translation](https://arxiv.org/abs/2010.11125) by Angela Fan, Shruti Bhosale, Holger Schwenk, Zhiyi Ma, Ahmed El-Kishky, Siddharth Goyal, Mandeep Baines, Onur Celebi, Guillaume Wenzek, Vishrav Chaudhary, Naman Goyal, Tom Birch, Vitaliy Liptchinsky, Sergey Edunov, Edouard Grave, Michael Auli, Armand Joulin.
 1. **[MarianMT](model_doc/marian)** Machine translation models trained using [OPUS](http://opus.nlpl.eu/) data by Jörg Tiedemann. The [Marian Framework](https://marian-nmt.github.io/) is being developed by the Microsoft Translator Team.
 1. **[MarkupLM](model_doc/markuplm)** (from Microsoft Research Asia) released with the paper [MarkupLM: Pre-training of Text and Markup Language for Visually-rich Document Understanding](https://arxiv.org/abs/2110.08518) by Junlong Li, Yiheng Xu, Lei Cui, Furu Wei.
+1. **[Mask2Former](model_doc/mask2former)** (from FAIR and UIUC) released with the paper [Masked-attention Mask Transformer for Universal Image Segmentation](https://arxiv.org/abs/2112.01527) by Bowen Cheng, Ishan Misra, Alexander G. Schwing, Alexander Kirillov, Rohit Girdhar.
 1. **[MaskFormer](model_doc/maskformer)** (from Meta and UIUC) released with the paper [Per-Pixel Classification is Not All You Need for Semantic Segmentation](https://arxiv.org/abs/2107.06278) by Bowen Cheng, Alexander G. Schwing, Alexander Kirillov.
 1. **[mBART](model_doc/mbart)** (from Facebook) released with the paper [Multilingual Denoising Pre-training for Neural Machine Translation](https://arxiv.org/abs/2001.08210) by Yinhan Liu, Jiatao Gu, Naman Goyal, Xian Li, Sergey Edunov, Marjan Ghazvininejad, Mike Lewis, Luke Zettlemoyer.
 1. **[mBART-50](model_doc/mbart)** (from Facebook) released with the paper [Multilingual Translation with Extensible Multilingual Pretraining and Finetuning](https://arxiv.org/abs/2008.00401) by Yuqing Tang, Chau Tran, Xian Li, Peng-Jen Chen, Naman Goyal, Vishrav Chaudhary, Jiatao Gu, Angela Fan.
@@ -306,6 +307,7 @@ Flax), PyTorch, and/or TensorFlow.
 |            M2M100             |       ✅       |       ❌       |       ✅        |         ❌         |      ❌      |
 |            Marian             |       ✅       |       ❌       |       ✅        |         ✅         |      ✅      |
 |           MarkupLM            |       ✅       |       ✅       |       ✅        |         ❌         |      ❌      |
+|          Mask2Former          |       ❌       |       ❌       |       ✅        |         ❌         |      ❌      |
 |          MaskFormer           |       ❌       |       ❌       |       ✅        |         ❌         |      ❌      |
 |        MaskFormerSwin         |       ❌       |       ❌       |       ❌        |         ❌         |      ❌      |
 |             mBART             |       ✅       |       ✅       |       ✅        |         ✅         |      ✅      |

--- a/docs/source/en/model_doc/mask2former.mdx
+++ b/docs/source/en/model_doc/mask2former.mdx
+<!--Copyright 2022 The HuggingFace Team. All rights reserved.
+Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with
+the License. You may obtain a copy of the License at
+http://www.apache.org/licenses/LICENSE-2.0
+Unless required by applicable law or agreed to in writing, software distributed under the License is distributed on
+an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. See the License for the
+specific language governing permissions and limitations under the License.
+-->
+# Mask2Former
+## Overview
+The Mask2Former model was proposed in [Masked-attention Mask Transformer for Universal Image Segmentation](https://arxiv.org/abs/2112.01527) by Bowen Cheng, Ishan Misra, Alexander G. Schwing, Alexander Kirillov, Rohit Girdhar. Mask2Former is a unified framework for panoptic, instance and semantic segmentation and features significant performance and efficiency improvements over [MaskFormer](maskformer).
+The abstract from the paper is the following:
+*Image segmentation groups pixels with different semantics, e.g., category or instance membership. Each choice
+of semantics defines a task. While only the semantics of each task differ, current research focuses on designing specialized architectures for each task. We present Masked-attention Mask Transformer (Mask2Former), a new architecture capable of addressing any image segmentation task (panoptic, instance or semantic). Its key components include masked attention, which extracts localized features by constraining cross-attention within predicted mask regions. In addition to reducing the research effort by at least three times, it outperforms the best specialized architectures by a significant margin on four popular datasets. Most notably, Mask2Former sets a new state-of-the-art for panoptic segmentation (57.8 PQ on COCO), instance segmentation (50.1 AP on COCO) and semantic segmentation (57.7 mIoU on ADE20K).*
+Tips:
+- Mask2Former uses the same preprocessing and postprocessing steps as [MaskFormer](maskformer). Use [`MaskFormerImageProcessor`] or [`AutoImageProcessor`] to prepare images and optional targets for the model.
+- To get the final segmentation, depending on the task, you can call [`~MaskFormerImageProcessor.post_process_semantic_segmentation`] or [`~MaskFormerImageProcessor.post_process_instance_segmentation`] or [`~MaskFormerImageProcessor.post_process_panoptic_segmentation`]. All three tasks can be solved using [`Mask2FormerForUniversalSegmentation`] output, panoptic segmentation accepts an optional `label_ids_to_fuse` argument to fuse instances of the target object/s (e.g. sky) together.
+This model was contributed by [Shivalika Singh](https://huggingface.co/shivi) and [Alara Dirik](https://huggingface.co/adirik). The original code can be found [here](https://github.com/facebookresearch/Mask2Former).
+## MaskFormer specific outputs
+[[autodoc]] models.mask2former.modeling_mask2former.Mask2FormerModelOutput
+[[autodoc]] models.mask2former.modeling_mask2former.Mask2FormerForUniversalSegmentationOutput
+## Mask2FormerConfig
+[[autodoc]] Mask2FormerConfig
+## Mask2FormerModel
+[[autodoc]] Mask2FormerModel
+    - forward
+## Mask2FormerForUniversalSegmentation
+[[autodoc]] Mask2FormerForUniversalSegmentation
+    - forward
--- a/docs/source/en/model_doc/maskformer.mdx
+++ b/docs/source/en/model_doc/maskformer.mdx
@@ -83,4 +83,4 @@ This model was contributed by [francesco](https://huggingface.co/francesco). The
 ## MaskFormerForInstanceSegmentation
 [[autodoc]] MaskFormerForInstanceSegmentation
    - forward
\ No newline at end of file
--- a/docs/source/es/index.mdx
+++ b/docs/source/es/index.mdx
@@ -100,6 +100,7 @@ La biblioteca actualmente contiene implementaciones de JAX, PyTorch y TensorFlow
 1. **[LXMERT](model_doc/lxmert)** (de UNC Chapel Hill) publicado con el paper [LXMERT: Learning Cross-Modality Encoder Representations from Transformers for Open-Domain Question Answering](https://arxiv.org/abs/1908.07490) por Hao Tan y Mohit Bansal.
 1. **[M2M100](model_doc/m2m_100)** (de Facebook) publicado con el paper [Beyond English-Centric Multilingual Machine Translation](https://arxiv.org/abs/2010.11125) por Angela Fan, Shruti Bhosale, Holger Schwenk, Zhiyi Ma, Ahmed El-Kishky, Siddharth Goyal, Mandeep Baines, Onur Celebi, Guillaume Wenzek, Vishrav Chaudhary, Naman Goyal, Tom Birch, Vitaliy Liptchinsky, Sergey Edunov, Edouard Grave, Michael Auli, Armand Joulin.
 1. **[MarianMT](model_doc/marian)** Modelos de traducción automática entrenados usando [OPUS](http://opus.nlpl.eu/) data por Jörg Tiedemann. El [Marian Framework](https://marian-nmt.github.io/) está siendo desarrollado por el equipo de traductores de Microsoft.
+1. **[Mask2Former](model_doc/mask2former)** (de FAIR y UIUC) publicado con el paper [Masked-attention Mask Transformer for Universal Image Segmentation](https://arxiv.org/abs/2112.01527) por Bowen Cheng, Ishan Misra, Alexander G. Schwing, Alexander Kirillov, Rohit Girdhar.
 1. **[MaskFormer](model_doc/maskformer)** (de Meta y UIUC) publicado con el paper [Per-Pixel Classification is Not All You Need for Semantic Segmentation](https://arxiv.org/abs/2107.06278) por Bowen Cheng, Alexander G. Schwing, Alexander Kirillov.
 1. **[MBart](model_doc/mbart)** (de Facebook) publicado con el paper [Multilingual Denoising Pre-training for Neural Machine Translation](https://arxiv.org/abs/2001.08210) por Yinhan Liu, Jiatao Gu, Naman Goyal, Xian Li, Sergey Edunov, Marjan Ghazvininejad, Mike Lewis, Luke Zettlemoyer.
 1. **[MBart-50](model_doc/mbart)** (de Facebook) publicado con el paper [Multilingual Translation with Extensible Multilingual Pretraining and Finetuning](https://arxiv.org/abs/2008.00401) por Yuqing Tang, Chau Tran, Xian Li, Peng-Jen Chen, Naman Goyal, Vishrav Chaudhary, Jiatao Gu, Angela Fan.

--- a/docs/source/it/index.mdx
+++ b/docs/source/it/index.mdx
@@ -109,7 +109,8 @@ La libreria attualmente contiene implementazioni in JAX, PyTorch e TensorFlow, p
 1. **[LXMERT](model_doc/lxmert)** (da UNC Chapel Hill) rilasciato con il paper [LXMERT: Learning Cross-Modality Encoder Representations from Transformers for Open-Domain Question Answering](https://arxiv.org/abs/1908.07490) da Hao Tan e Mohit Bansal.
 1. **[M2M100](model_doc/m2m_100)** (da Facebook) rilasciato con il paper [Beyond English-Centric Multilingual Machine Translation](https://arxiv.org/abs/2010.11125) da Angela Fan, Shruti Bhosale, Holger Schwenk, Zhiyi Ma, Ahmed El-Kishky, Siddharth Goyal, Mandeep Baines, Onur Celebi, Guillaume Wenzek, Vishrav Chaudhary, Naman Goyal, Tom Birch, Vitaliy Liptchinsky, Sergey Edunov, Edouard Grave, Michael Auli, Armand Joulin.
 1. **[MarianMT](model_doc/marian)** Modello di machine learning per le traduzioni allenato utilizzando i dati [OPUS](http://opus.nlpl.eu/) di Jörg Tiedemann. Il [Framework Marian](https://marian-nmt.github.io/) è stato sviluppato dal Microsoft Translator Team.
-1. **[MaskFormer](model_doc/maskformer)** (da Meta and UIUC) rilasciato con il paper [Per-Pixel Classification is Not All You Need for Semantic Segmentation](https://arxiv.org/abs/2107.06278) da Bowen Cheng, Alexander G. Schwing, Alexander Kirillov.
+1. **[Mask2Former](model_doc/mask2former)** (da FAIR e UIUC) rilasciato con il paper [Masked-attention Mask Transformer for Universal Image Segmentation](https://arxiv.org/abs/2112.01527) da Bowen Cheng, Ishan Misra, Alexander G. Schwing, Alexander Kirillov, Rohit Girdhar.
+1. **[MaskFormer](model_doc/maskformer)** (da Meta e UIUC) rilasciato con il paper [Per-Pixel Classification is Not All You Need for Semantic Segmentation](https://arxiv.org/abs/2107.06278) da Bowen Cheng, Alexander G. Schwing, Alexander Kirillov.
 1. **[MBart](model_doc/mbart)** (da Facebook) rilasciato con il paper [Multilingual Denoising Pre-training for Neural Machine Translation](https://arxiv.org/abs/2001.08210) da Yinhan Liu, Jiatao Gu, Naman Goyal, Xian Li, Sergey Edunov, Marjan Ghazvininejad, Mike Lewis, Luke Zettlemoyer.
 1. **[MBart-50](model_doc/mbart)** (da Facebook) rilasciato con il paper [Multilingual Translation with Extensible Multilingual Pretraining and Finetuning](https://arxiv.org/abs/2008.00401) da Yuqing Tang, Chau Tran, Xian Li, Peng-Jen Chen, Naman Goyal, Vishrav Chaudhary, Jiatao Gu, Angela Fan.
 1. **[Megatron-BERT](model_doc/megatron-bert)** (da NVIDIA) rilasciato con il paper [Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism](https://arxiv.org/abs/1909.08053) da Mohammad Shoeybi, Mostofa Patwary, Raul Puri, Patrick LeGresley, Jared Casper e Bryan Catanzaro.

--- a/docs/source/ko/index.mdx
+++ b/docs/source/ko/index.mdx
@@ -124,6 +124,7 @@ specific language governing permissions and limitations under the License.
 1. **[M2M100](model_doc/m2m_100)** (from Facebook) released with the paper [Beyond English-Centric Multilingual Machine Translation](https://arxiv.org/abs/2010.11125) by Angela Fan, Shruti Bhosale, Holger Schwenk, Zhiyi Ma, Ahmed El-Kishky, Siddharth Goyal, Mandeep Baines, Onur Celebi, Guillaume Wenzek, Vishrav Chaudhary, Naman Goyal, Tom Birch, Vitaliy Liptchinsky, Sergey Edunov, Edouard Grave, Michael Auli, Armand Joulin.
 1. **[MarianMT](model_doc/marian)** Machine translation models trained using [OPUS](http://opus.nlpl.eu/) data by Jörg Tiedemann. The [Marian Framework](https://marian-nmt.github.io/) is being developed by the Microsoft Translator Team.
 1. **[MarkupLM](model_doc/markuplm)** (from Microsoft Research Asia) released with the paper [MarkupLM: Pre-training of Text and Markup Language for Visually-rich Document Understanding](https://arxiv.org/abs/2110.08518) by Junlong Li, Yiheng Xu, Lei Cui, Furu Wei.
+1. **[Mask2Former](model_doc/mask2former)** (from FAIR and UIUC) released with the paper [Masked-attention Mask Transformer for Universal Image Segmentation](https://arxiv.org/abs/2112.01527) by Bowen Cheng, Ishan Misra, Alexander G. Schwing, Alexander Kirillov, Rohit Girdhar.
 1. **[MaskFormer](model_doc/maskformer)** (from Meta and UIUC) released with the paper [Per-Pixel Classification is Not All You Need for Semantic Segmentation](https://arxiv.org/abs/2107.06278) by Bowen Cheng, Alexander G. Schwing, Alexander Kirillov.
 1. **[mBART](model_doc/mbart)** (from Facebook) released with the paper [Multilingual Denoising Pre-training for Neural Machine Translation](https://arxiv.org/abs/2001.08210) by Yinhan Liu, Jiatao Gu, Naman Goyal, Xian Li, Sergey Edunov, Marjan Ghazvininejad, Mike Lewis, Luke Zettlemoyer.
 1. **[mBART-50](model_doc/mbart)** (from Facebook) released with the paper [Multilingual Translation with Extensible Multilingual Pretraining and Finetuning](https://arxiv.org/abs/2008.00401) by Yuqing Tang, Chau Tran, Xian Li, Peng-Jen Chen, Naman Goyal, Vishrav Chaudhary, Jiatao Gu, Angela Fan.

--- a/docs/source/pt/index.mdx
+++ b/docs/source/pt/index.mdx
@@ -114,6 +114,7 @@ Atualmente a biblioteca contém implementações do PyTorch, TensorFlow e JAX, p
 1. **[LXMERT](model_doc/lxmert)** (from UNC Chapel Hill) released with the paper [LXMERT: Learning Cross-Modality Encoder Representations from Transformers for Open-Domain Question Answering](https://arxiv.org/abs/1908.07490) by Hao Tan and Mohit Bansal.
 1. **[M2M100](model_doc/m2m_100)** (from Facebook) released with the paper [Beyond English-Centric Multilingual Machine Translation](https://arxiv.org/abs/2010.11125) by Angela Fan, Shruti Bhosale, Holger Schwenk, Zhiyi Ma, Ahmed El-Kishky, Siddharth Goyal, Mandeep Baines, Onur Celebi, Guillaume Wenzek, Vishrav Chaudhary, Naman Goyal, Tom Birch, Vitaliy Liptchinsky, Sergey Edunov, Edouard Grave, Michael Auli, Armand Joulin.
 1. **[MarianMT](model_doc/marian)** Machine translation models trained using [OPUS](http://opus.nlpl.eu/) data by Jörg Tiedemann. The [Marian Framework](https://marian-nmt.github.io/) is being developed by the Microsoft Translator Team.
+1. **[Mask2Former](model_doc/mask2former)** (from FAIR and UIUC) released with the paper [Masked-attention Mask Transformer for Universal Image Segmentation](https://arxiv.org/abs/2112.01527) by Bowen Cheng, Ishan Misra, Alexander G. Schwing, Alexander Kirillov, Rohit Girdhar.
 1. **[MaskFormer](model_doc/maskformer)** (from Meta and UIUC) released with the paper [Per-Pixel Classification is Not All You Need for Semantic Segmentation](https://arxiv.org/abs/2107.06278) by Bowen Cheng, Alexander G. Schwing, Alexander Kirillov.
 1. **[MBart](model_doc/mbart)** (from Facebook) released with the paper [Multilingual Denoising Pre-training for Neural Machine Translation](https://arxiv.org/abs/2001.08210) by Yinhan Liu, Jiatao Gu, Naman Goyal, Xian Li, Sergey Edunov, Marjan Ghazvininejad, Mike Lewis, Luke Zettlemoyer.
 1. **[MBart-50](model_doc/mbart)** (from Facebook) released with the paper [Multilingual Translation with Extensible Multilingual Pretraining and Finetuning](https://arxiv.org/abs/2008.00401) by Yuqing Tang, Chau Tran, Xian Li, Peng-Jen Chen, Naman Goyal, Vishrav Chaudhary, Jiatao Gu, Angela Fan.

--- a/src/transformers/__init__.py
+++ b/src/transformers/__init__.py
@@ -322,6 +322,10 @@ _import_structure = {
        "MarkupLMProcessor",
        "MarkupLMTokenizer",
    ],
+    "models.mask2former": [
+        "MASK2FORMER_PRETRAINED_CONFIG_ARCHIVE_MAP",
+        "Mask2FormerConfig",
+    ],
    "models.maskformer": ["MASKFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP", "MaskFormerConfig", "MaskFormerSwinConfig"],
    "models.mbart": ["MBartConfig"],
    "models.mbart50": [],
@@ -1708,6 +1712,14 @@ else:
            "MarkupLMPreTrainedModel",
        ]
    )
+    _import_structure["models.mask2former"].extend(
+        [
+            "MASK2FORMER_PRETRAINED_MODEL_ARCHIVE_LIST",
+            "Mask2FormerForUniversalSegmentation",
+            "Mask2FormerModel",
+            "Mask2FormerPreTrainedModel",
+        ]
+    )
    _import_structure["models.maskformer"].extend(
        [
            "MASKFORMER_PRETRAINED_MODEL_ARCHIVE_LIST",
@@ -3695,6 +3707,7 @@ if TYPE_CHECKING:
        MarkupLMProcessor,
        MarkupLMTokenizer,
    )
+    from .models.mask2former import MASK2FORMER_PRETRAINED_CONFIG_ARCHIVE_MAP, Mask2FormerConfig
    from .models.maskformer import MASKFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP, MaskFormerConfig, MaskFormerSwinConfig
    from .models.mbart import MBartConfig
    from .models.mctct import MCTCT_PRETRAINED_CONFIG_ARCHIVE_MAP, MCTCTConfig, MCTCTProcessor
@@ -4857,6 +4870,12 @@ if TYPE_CHECKING:
            MarkupLMModel,
            MarkupLMPreTrainedModel,
        )
+        from .models.mask2former import (
+            MASK2FORMER_PRETRAINED_MODEL_ARCHIVE_LIST,
+            Mask2FormerForUniversalSegmentation,
+            Mask2FormerModel,
+            Mask2FormerPreTrainedModel,
+        )
        from .models.maskformer import (
            MASKFORMER_PRETRAINED_MODEL_ARCHIVE_LIST,
            MaskFormerForInstanceSegmentation,

--- a/src/transformers/models/__init__.py
+++ b/src/transformers/models/__init__.py
@@ -102,6 +102,7 @@ from . import (
    m2m_100,
    marian,
    markuplm,
+    mask2former,
    maskformer,
    mbart,
    mbart50,

--- a/src/transformers/models/auto/configuration_auto.py
+++ b/src/transformers/models/auto/configuration_auto.py
@@ -104,6 +104,7 @@ CONFIG_MAPPING_NAMES = OrderedDict(
        ("m2m_100", "M2M100Config"),
        ("marian", "MarianConfig"),
        ("markuplm", "MarkupLMConfig"),
+        ("mask2former", "Mask2FormerConfig"),
        ("maskformer", "MaskFormerConfig"),
        ("maskformer-swin", "MaskFormerSwinConfig"),
        ("mbart", "MBartConfig"),
@@ -262,6 +263,7 @@ CONFIG_ARCHIVE_MAP_MAPPING_NAMES = OrderedDict(
        ("lxmert", "LXMERT_PRETRAINED_CONFIG_ARCHIVE_MAP"),
        ("m2m_100", "M2M_100_PRETRAINED_CONFIG_ARCHIVE_MAP"),
        ("markuplm", "MARKUPLM_PRETRAINED_CONFIG_ARCHIVE_MAP"),
+        ("mask2former", "MASK2FORMER_PRETRAINED_CONFIG_ARCHIVE_MAP"),
        ("maskformer", "MASKFORMER_PRETRAINED_CONFIG_ARCHIVE_MAP"),
        ("mbart", "MBART_PRETRAINED_CONFIG_ARCHIVE_MAP"),
        ("mctct", "MCTCT_PRETRAINED_CONFIG_ARCHIVE_MAP"),
@@ -425,6 +427,7 @@ MODEL_NAMES_MAPPING = OrderedDict(
        ("m2m_100", "M2M100"),
        ("marian", "Marian"),
        ("markuplm", "MarkupLM"),
+        ("mask2former", "Mask2Former"),
        ("maskformer", "MaskFormer"),
        ("maskformer-swin", "MaskFormerSwin"),
        ("mbart", "mBART"),

--- a/src/transformers/models/auto/image_processing_auto.py
+++ b/src/transformers/models/auto/image_processing_auto.py
@@ -61,6 +61,7 @@ IMAGE_PROCESSOR_MAPPING_NAMES = OrderedDict(
        ("layoutlmv2", "LayoutLMv2ImageProcessor"),
        ("layoutlmv3", "LayoutLMv3ImageProcessor"),
        ("levit", "LevitImageProcessor"),
+        ("mask2former", "MaskFormerImageProcessor"),
        ("maskformer", "MaskFormerImageProcessor"),
        ("mobilenet_v1", "MobileNetV1ImageProcessor"),
        ("mobilenet_v2", "MobileNetV2ImageProcessor"),