-`Nov 18, 2022`: 🚀 InternImage-XL merged into [BEVFormer v2](https://arxiv.org/abs/2211.10439) achieves stae-of-the-art performance of `63.4 NDS` on nuScenes Camera Only.
-`Nov 10, 2022`: 🚀🚀 InternImage-H achieves a new record `65.4 mAP` on COCO detection test-dev and `62.9 mIoU` on
ADE20K, outperforming previous models by a large margin.
## Coming soon
- [ ] Classification/detection/segmentation code of the InternImage series.
**InternImage**, initially described in [arxiv](https://arxiv.org/abs/2211.05778), can be a general backbone for computer vision.
It takes deformable convolution as the core operator to obtain large effective receptive fields, and introducing adaptive spatial aggregation
to reduces the strict inductive bias. Our model makes it possible to learn more stronger and robust models with large-scale parameters from massive data.
<divalign=center>
<imgsrc='./figs/arch.png'width=400>
</div>
## Main Results on ImageNet with Pretrained Models
**ImageNet-1K and ImageNet-22K Pretrained InternImage Models**
