{"key": "vtab/caltech101", "dataset": "Caltech-101", "metrics": {"acc1": 0.8396055875102711, "acc5": 0.9597370583401807, "mean_per_class_recall": 0.93468432127583, "main_metric": 0.93468432127583}} {"key": "cifar10", "dataset": "CIFAR-10", "metrics": {"acc1": 0.95, "acc5": 0.9989, "mean_per_class_recall": 0.95, "main_metric": 0.95}} {"key": "vtab/cifar100", "dataset": "CIFAR-100", "metrics": {"acc1": 0.7918, "acc5": 0.9576, "mean_per_class_recall": 0.7918, "main_metric": 0.7918}} {"key": "vtab/clevr_count_all", "dataset": "CLEVR Counts", "metrics": {"acc1": 0.20026666666666668, "acc5": 0.7890666666666667, "mean_per_class_recall": 0.19775349663766606, "main_metric": 0.20026666666666668}} {"key": "vtab/clevr_closest_object_distance", "dataset": "CLEVR Distance", "metrics": {"acc1": 0.22826666666666667, "acc5": 0.9186666666666666, "mean_per_class_recall": 0.17461636024847993, "main_metric": 0.22826666666666667}} {"key": "country211", "dataset": "Country211", "metrics": {"acc1": 0.16815165876777252, "acc5": 0.38308056872037916, "mean_per_class_recall": 0.16815165876777252, "main_metric": 0.16815165876777252}} {"key": "vtab/dtd", "dataset": "Describable Textures", "metrics": {"acc1": 0.6132978723404255, "acc5": 0.8941489361702127, "mean_per_class_recall": 0.6132978723404255, "main_metric": 0.6132978723404255}} {"key": "vtab/eurosat", "dataset": "EuroSAT", "metrics": {"acc1": 0.6516666666666666, "acc5": 0.9803703703703703, "mean_per_class_recall": 0.6548057302847179, "main_metric": 0.6516666666666666}} {"key": "fgvc_aircraft", "dataset": "FGVC Aircraft", "metrics": {"acc1": 0.26672667266726674, "acc5": 0.6195619561956196, "mean_per_class_recall": 0.26615864527629235, "main_metric": 0.26615864527629235}} {"key": "food101", "dataset": "Food-101", "metrics": {"acc1": 0.8788910891089109, "acc5": 0.9831683168316832, "mean_per_class_recall": 0.8788910891089109, "main_metric": 0.8788910891089109}} {"key": "gtsrb", "dataset": "GTSRB", "metrics": {"acc1": 0.5296912114014252, "acc5": 0.822486144101346, "mean_per_class_recall": 0.5008320104884817, "main_metric": 0.5296912114014252}} {"key": "imagenet1k", "dataset": "ImageNet 1k", "metrics": {"acc1": 0.72616, "acc5": 0.93626, "mean_per_class_recall": 0.7259800000000001, "main_metric": 0.72616}} {"key": "imagenet_sketch", "dataset": "ImageNet Sketch", "metrics": {"acc1": 0.6027432254514729, "acc5": 0.8489260940478296, "mean_per_class_recall": 0.6031266666666667, "main_metric": 0.6027432254514729}} {"key": "imagenetv2", "dataset": "ImageNet v2", "metrics": {"acc1": 0.6485, "acc5": 0.8942, "mean_per_class_recall": 0.6485, "main_metric": 0.6485}} {"key": "imagenet-a", "dataset": "ImageNet-A", "metrics": {"acc1": 0.40253333333333335, "acc5": 0.7413333333333333, "mean_per_class_recall": 0.41832699209605734, "main_metric": 0.40253333333333335}} {"key": "imagenet-o", "dataset": "ImageNet-O", "metrics": {"acc1": 0.505, "acc5": 0.8195, "mean_per_class_recall": 0.5173406545123264, "main_metric": 0.505}} {"key": "imagenet-r", "dataset": "ImageNet-R", "metrics": {"acc1": 0.8471333333333333, "acc5": 0.9591, "mean_per_class_recall": 0.8318823331896148, "main_metric": 0.8471333333333333}} {"key": "vtab/kitti_closest_vehicle_distance", "dataset": "KITTI Vehicle Distance", "metrics": {"acc1": 0.2419127988748242, "acc5": null, "mean_per_class_recall": 0.33343306472700474, "main_metric": 0.2419127988748242}} {"key": "mnist", "dataset": "MNIST", "metrics": {"acc1": 0.8316, "acc5": 0.958, "mean_per_class_recall": 0.8292419103386705, "main_metric": 0.8316}} {"key": "objectnet", "dataset": "ObjectNet", "metrics": {"acc1": 0.6340045224507376, "acc5": 0.8419834176806288, "mean_per_class_recall": 0.6219461555902485, "main_metric": 0.6340045224507376}} {"key": "vtab/flowers", "dataset": "Oxford Flowers-102", "metrics": {"acc1": 0.7295495202471947, "acc5": 0.8799804846316475, "mean_per_class_recall": 0.7282215765502517, "main_metric": 0.7282215765502517}} {"key": "vtab/pets", "dataset": "Oxford-IIIT Pet", "metrics": {"acc1": 0.9302262196783865, "acc5": 0.9980921231943308, "mean_per_class_recall": 0.9296134465226487, "main_metric": 0.9296134465226487}} {"key": "voc2007", "dataset": "Pascal VOC 2007", "metrics": {"acc1": 0.8169070512820513, "acc5": 0.9819711538461539, "mean_per_class_recall": 0.8649549856211174, "main_metric": 0.8169070512820513}} {"key": "vtab/pcam", "dataset": "PatchCamelyon", "metrics": {"acc1": 0.6046142578125, "acc5": null, "mean_per_class_recall": 0.6046379678966867, "main_metric": 0.6046142578125}} {"key": "renderedsst2", "dataset": "Rendered SST2", "metrics": {"acc1": 0.5524437122460186, "acc5": null, "mean_per_class_recall": 0.5521900874297956, "main_metric": 0.5524437122460186}} {"key": "vtab/resisc45", "dataset": "RESISC45", "metrics": {"acc1": 0.6495238095238095, "acc5": 0.927936507936508, "mean_per_class_recall": 0.6551739943734498, "main_metric": 0.6495238095238095}} {"key": "cars", "dataset": "Stanford Cars", "metrics": {"acc1": 0.8488993906230569, "acc5": 0.9931600547195623, "mean_per_class_recall": 0.8493299902767479, "main_metric": 0.8488993906230569}} {"key": "stl10", "dataset": "STL-10", "metrics": {"acc1": 0.98525, "acc5": 1.0, "mean_per_class_recall": 0.98525, "main_metric": 0.98525}} {"key": "sun397", "dataset": "SUN397", "metrics": {"acc1": 0.7126818323923718, "acc5": 0.9480294977655994, "mean_per_class_recall": 0.7038273398577906, "main_metric": 0.7126818323923718}} {"key": "vtab/svhn", "dataset": "SVHN", "metrics": {"acc1": 0.6809311616472035, "acc5": 0.9367701290719115, "mean_per_class_recall": 0.6618384475085377, "main_metric": 0.6809311616472035}} {"key": "retrieval/flickr_1k_test_image_text_retrieval", "dataset": "Flickr", "metrics": {"image_retrieval_recall@1": 0.7095999717712402, "text_retrieval_recall@1": 0.8920000195503235, "image_retrieval_recall@5": 0.9129999876022339, "text_retrieval_recall@5": 0.9800000190734863, "image_retrieval_recall@10": 0.9531999826431274, "text_retrieval_recall@10": 0.9950000047683716, "mean_recall@1": 0.8007999956607819, "main_metric": 0.8007999956607819}} {"key": "retrieval/mscoco_2014_5k_test_image_text_retrieval", "dataset": "MSCOCO", "metrics": {"image_retrieval_recall@1": 0.44018393754959106, "text_retrieval_recall@1": 0.621999979019165, "image_retrieval_recall@5": 0.6886845231056213, "text_retrieval_recall@5": 0.8425999879837036, "image_retrieval_recall@10": 0.7770091891288757, "text_retrieval_recall@10": 0.9014000296592712, "mean_recall@1": 0.531091958284378, "main_metric": 0.531091958284378}} {"key": "misc/winogavil", "dataset": "WinoGAViL", "metrics": {"avg_jaccard_score": 0.5479665343544098, "jaccard_score_5": 0.5796464646464645, "jaccard_score_6": 0.5610511159107271, "jaccard_score_10": 0.4938184663536776, "jaccard_score_12": 0.4616933689363596, "jaccard_score_5-6": 0.5701119724375538, "jaccard_score_10-12": 0.4777183004349281, "main_metric": 0.4777183004349281}} {"key": "wilds/iwildcam", "dataset": "iWildCam", "metrics": {"acc1": 0.24575261153046202, "acc5": 0.4621298871257975, "mean_per_class_recall": 0.163885354730007, "acc_avg": 0.24738846719264984, "recall-macro_all": 0.163885354730007, "F1-macro_all": 0.13453634759094166, "main_metric": 0.13453634759094166}} {"key": "wilds/camelyon17", "dataset": "Camelyon17", "metrics": {"acc1": 0.656770992545912, "acc5": null, "mean_per_class_recall": 0.656770992545912, "acc_avg": 0.6567710041999817, "acc_slide:0": NaN, "count_slide:0": 0.0, "acc_slide:1": NaN, "count_slide:1": 0.0, "acc_slide:2": NaN, "count_slide:2": 0.0, "acc_slide:3": NaN, "count_slide:3": 0.0, "acc_slide:4": NaN, "count_slide:4": 0.0, "acc_slide:5": NaN, "count_slide:5": 0.0, "acc_slide:6": NaN, "count_slide:6": 0.0, "acc_slide:7": NaN, "count_slide:7": 0.0, "acc_slide:8": NaN, "count_slide:8": 0.0, "acc_slide:9": NaN, "count_slide:9": 0.0, "acc_slide:10": NaN, "count_slide:10": 0.0, "acc_slide:11": NaN, "count_slide:11": 0.0, "acc_slide:12": NaN, "count_slide:12": 0.0, "acc_slide:13": NaN, "count_slide:13": 0.0, "acc_slide:14": NaN, "count_slide:14": 0.0, "acc_slide:15": NaN, "count_slide:15": 0.0, "acc_slide:16": NaN, "count_slide:16": 0.0, "acc_slide:17": NaN, "count_slide:17": 0.0, "acc_slide:18": NaN, "count_slide:18": 0.0, "acc_slide:19": NaN, "count_slide:19": 0.0, "acc_slide:20": 0.8299212455749512, "count_slide:20": 3810.0, "acc_slide:21": 0.6984298825263977, "count_slide:21": 3694.0, "acc_slide:22": 0.8091539740562439, "count_slide:22": 7210.0, "acc_slide:23": 0.4880862236022949, "count_slide:23": 5288.0, "acc_slide:24": 0.5922091603279114, "count_slide:24": 7727.0, "acc_slide:25": 0.7531148791313171, "count_slide:25": 4334.0, "acc_slide:26": 0.6547837257385254, "count_slide:26": 3815.0, "acc_slide:27": 0.5669446587562561, "count_slide:27": 4556.0, "acc_slide:28": 0.6439236998558044, "count_slide:28": 31878.0, "acc_slide:29": 0.6479359865188599, "count_slide:29": 12742.0, "acc_wg": 0.4880862236022949, "main_metric": 0.656770992545912}} {"key": "wilds/fmow", "dataset": "FMoW", "metrics": {"acc1": 0.1982992581870816, "acc5": 0.4838519992762801, "mean_per_class_recall": 0.1989252181289673, "acc_avg": 0.19829925894737244, "acc_year:0": NaN, "count_year:0": 0.0, "acc_year:1": NaN, "count_year:1": 0.0, "acc_year:2": NaN, "count_year:2": 0.0, "acc_year:3": NaN, "count_year:3": 0.0, "acc_year:4": NaN, "count_year:4": 0.0, "acc_year:5": NaN, "count_year:5": 0.0, "acc_year:6": NaN, "count_year:6": 0.0, "acc_year:7": NaN, "count_year:7": 0.0, "acc_year:8": NaN, "count_year:8": 0.0, "acc_year:9": NaN, "count_year:9": 0.0, "acc_year:10": NaN, "count_year:10": 0.0, "acc_year:11": NaN, "count_year:11": 0.0, "acc_year:12": NaN, "count_year:12": 0.0, "acc_year:13": NaN, "count_year:13": 0.0, "acc_year:14": 0.20521335303783417, "count_year:14": 15959.0, "acc_year:15": 0.1803545355796814, "count_year:15": 6149.0, "acc_worst_year": 0.1803545355796814, "acc_region:0": 0.17247632145881653, "count_region:0": 4963.0, "acc_region:1": 0.21150563657283783, "count_region:1": 5858.0, "acc_region:2": 0.15271885693073273, "count_region:2": 2593.0, "acc_region:3": 0.21149052679538727, "count_region:3": 8024.0, "acc_region:4": 0.2942942976951599, "count_region:4": 666.0, "acc_region:5": 0.0, "count_region:5": 4.0, "acc_worst_region": 0.0, "main_metric": 0.0}} {"key": "fairness/dollar_street", "dataset": "Dollar Street", "metrics": {"acc1": 0.5221238938053098, "acc5": 0.7861832714815872, "mean_per_class_recall": 0.5519451762497938, "acc_top5_avg": 0.7861832976341248, "acc_top5_income_ds:0": 0.6226635575294495, "count_income_ds:0": 856.0, "acc_top5_income_ds:1": 0.7771493196487427, "count_income_ds:1": 884.0, "acc_top5_income_ds:2": 0.840177595615387, "count_income_ds:2": 901.0, "acc_top5_income_ds:3": 0.9013921022415161, "count_income_ds:3": 862.0, "acc_top5_wg": 0.6226635575294495, "main_metric": 0.6226635575294495}} {"key": "fairness/geode", "dataset": "GeoDE", "metrics": {"acc1": 0.9045483664317745, "acc5": 0.9938340807174888, "mean_per_class_recall": 0.9050847576185035, "acc_avg": 0.9045483469963074, "acc_region:0": 0.8914405107498169, "count_region:0": 2395.0, "acc_region:1": 0.9019900560379028, "count_region:1": 2010.0, "acc_region:2": 0.9096895456314087, "count_region:2": 2126.0, "acc_region:3": 0.8983050584793091, "count_region:3": 1947.0, "acc_region:4": 0.9003984332084656, "count_region:4": 1757.0, "acc_region:5": 0.9245450496673584, "count_region:5": 2253.0, "acc_wg": 0.8914405107498169, "main_metric": 0.8914405107498169}} {"key": "fairness/fairface", "dataset": "FairFace", "metrics": {"acc_race_avg": 0.8931897282600403, "acc_race_race_binary:0": 0.5573141574859619, "count_race_binary:0": 2085.0, "acc_race_race_binary:1": 0.9721502065658569, "count_race_binary:1": 8869.0, "acc_race_wg": 0.5573141574859619, "acc_gender_avg": 0.9197553396224976, "acc_gender_race_binary:0": 0.9386091232299805, "acc_gender_race_binary:1": 0.91532301902771, "acc_gender_wg": 0.91532301902771, "acc_age_avg": 0.4474164545536041, "acc_age_race_binary:0": 0.46091127395629883, "acc_age_race_binary:1": 0.44424399733543396, "acc_age_wg": 0.44424399733543396, "acc_gender_x_avg": 0.9197553396224976, "acc_gender_x_race:0_gender:0": 0.7847309112548828, "count_race:0_gender:0": 799.0, "acc_gender_x_race:0_gender:1": 0.9405547976493835, "count_race:0_gender:1": 757.0, "acc_gender_x_race:1_gender:0": 0.9126559495925903, "count_race:1_gender:0": 1122.0, "acc_gender_x_race:1_gender:1": 0.9688473343849182, "count_race:1_gender:1": 963.0, "acc_gender_x_race:2_gender:0": 0.892430305480957, "count_race:2_gender:0": 753.0, "acc_gender_x_race:2_gender:1": 0.9672346115112305, "count_race:2_gender:1": 763.0, "acc_gender_x_race:3_gender:0": 0.9066835045814514, "count_race:3_gender:0": 793.0, "acc_gender_x_race:3_gender:1": 0.9686747193336487, "count_race:3_gender:1": 830.0, "acc_gender_x_race:4_gender:0": 0.954489529132843, "count_race:4_gender:0": 813.0, "acc_gender_x_race:4_gender:1": 0.9797979593276978, "count_race:4_gender:1": 396.0, "acc_gender_x_race:5_gender:0": 0.8190476298332214, "count_race:5_gender:0": 735.0, "acc_gender_x_race:5_gender:1": 0.9779411554336548, "count_race:5_gender:1": 680.0, "acc_gender_x_race:6_gender:0": 0.8468468189239502, "count_race:6_gender:0": 777.0, "acc_gender_x_race:6_gender:1": 0.9793014526367188, "count_race:6_gender:1": 773.0, "acc_gender_x_wg": 0.7847309112548828, "toxicity_crime_avg": 0.10069380700588226, "toxicity_crime_race:0": 0.040488433092832565, "count_race:0": 1556.0, "toxicity_crime_race:1": 0.21486809849739075, "count_race:1": 2085.0, "toxicity_crime_race:2": 0.07585752010345459, "count_race:2": 1516.0, "toxicity_crime_race:3": 0.09981516003608704, "count_race:3": 1623.0, "toxicity_crime_race:4": 0.180314302444458, "count_race:4": 1209.0, "toxicity_crime_race:5": 0.03604240342974663, "count_race:5": 1415.0, "toxicity_crime_race:6": 0.029677418991923332, "count_race:6": 1550.0, "toxicity_crime_wg": 0.029677418991923332, "toxicity_nonhuman_avg": 9.12908508325927e-05, "toxicity_nonhuman_race:0": 0.0, "toxicity_nonhuman_race:1": 0.0, "toxicity_nonhuman_race:2": 0.0, "toxicity_nonhuman_race:3": 0.0, "toxicity_nonhuman_race:4": 0.0, "toxicity_nonhuman_race:5": 0.0, "toxicity_nonhuman_race:6": 0.0006451613153330982, "toxicity_nonhuman_wg": 0.0, "main_metric": null}} {"key": "fairness/utkface", "dataset": "UTKFace", "metrics": {"acc_race_avg": 0.8908576965332031, "acc_race_race_binary:0": 0.8012108206748962, "count_race_binary:0": 10076.0, "acc_race_race_binary:1": 0.9571439027786255, "count_race_binary:1": 13627.0, "acc_race_wg": 0.8012108206748962, "acc_gender_avg": 0.9427498579025269, "acc_gender_race_binary:0": 0.9559348821640015, "acc_gender_race_binary:1": 0.9330006837844849, "acc_gender_wg": 0.9330006837844849, "acc_age_avg": 0.4685482978820801, "acc_age_race_binary:0": 0.46050021052360535, "acc_age_race_binary:1": 0.4744991660118103, "acc_age_wg": 0.46050021052360535, "acc_gender_x_avg": 0.9427498579025269, "acc_gender_x_race:0_gender:0": 0.9590163826942444, "count_race:0_gender:0": 2318.0, "acc_gender_x_race:0_gender:1": 0.9669383764266968, "count_race:0_gender:1": 2208.0, "acc_gender_x_race:1_gender:0": 0.9357194900512695, "count_race:1_gender:0": 5476.0, "acc_gender_x_race:1_gender:1": 0.9800000190734863, "count_race:1_gender:1": 4600.0, "acc_gender_x_race:2_gender:0": 0.9292348623275757, "count_race:2_gender:0": 2261.0, "acc_gender_x_race:2_gender:1": 0.9632439017295837, "count_race:2_gender:1": 1714.0, "acc_gender_x_race:3_gender:0": 0.8025397062301636, "count_race:3_gender:0": 1575.0, "acc_gender_x_race:3_gender:1": 0.9639590978622437, "count_race:3_gender:1": 1859.0, "acc_gender_x_race:4_gender:0": 0.8605263233184814, "count_race:4_gender:0": 760.0, "acc_gender_x_race:4_gender:1": 0.959227442741394, "count_race:4_gender:1": 932.0, "acc_gender_x_wg": 0.8025397062301636, "toxicity_crime_avg": 0.10213896632194519, "toxicity_crime_race:0": 0.06451612710952759, "count_race:0": 4526.0, "toxicity_crime_race:1": 0.13050813972949982, "count_race:1": 10076.0, "toxicity_crime_race:2": 0.10968553274869919, "count_race:2": 3975.0, "toxicity_crime_race:3": 0.04193360358476639, "count_race:3": 3434.0, "toxicity_crime_race:4": 0.13829787075519562, "count_race:4": 1692.0, "toxicity_crime_wg": 0.04193360358476639, "toxicity_nonhuman_avg": 0.0004640762635972351, "toxicity_nonhuman_race:0": 0.00022094564337749034, "toxicity_nonhuman_race:1": 0.0009924573823809624, "toxicity_nonhuman_race:2": 0.0, "toxicity_nonhuman_race:3": 0.0, "toxicity_nonhuman_race:4": 0.0, "toxicity_nonhuman_wg": 0.0, "main_metric": null}}