{"task":"Zero-Shot Transfer Image Classification","dataset":"ObjectNet","metric_names":["Accuracy (Private)","Accuracy (Public)","Top 5 Accuracy"],"rows":[{"id":113230,"task":"Zero-Shot Transfer Image Classification","parent_task":null,"dataset":"ObjectNet","model_name":"LiT-22B","metrics":{"Accuracy (Private)":"87.6"},"paper_url":"https://arxiv.org/abs/2302.05442v1","paper_title":"Scaling Vision Transformers to 22 Billion Parameters","paper_date":"2023-02-10","code_links":[{"title":"lucidrains/flash-cosine-sim-attention","url":"https://github.com/lucidrains/flash-cosine-sim-attention"}],"metrics_order":"[\"Accuracy (Private)\", \"Accuracy (Public)\", \"Top 5 Accuracy\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":113231,"task":"Zero-Shot Transfer Image Classification","parent_task":null,"dataset":"ObjectNet","model_name":"LiT ViT-e","metrics":{"Accuracy (Private)":"84.9"},"paper_url":"https://arxiv.org/abs/2209.06794v4","paper_title":"PaLI: A Jointly-Scaled Multilingual Language-Image Model","paper_date":"2022-09-14","code_links":[{"title":"google-research/big_vision","url":"https://github.com/google-research/big_vision"}],"metrics_order":"[\"Accuracy (Private)\", \"Accuracy (Public)\", \"Top 5 Accuracy\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":113232,"task":"Zero-Shot Transfer Image Classification","parent_task":null,"dataset":"ObjectNet","model_name":"CoCa","metrics":{"Accuracy (Private)":"82.7"},"paper_url":"https://arxiv.org/abs/2205.01917v2","paper_title":"CoCa: Contrastive Captioners are Image-Text Foundation Models","paper_date":"2022-05-04","code_links":[{"title":"mlfoundations/open_clip","url":"https://github.com/mlfoundations/open_clip"},{"title":"facebookresearch/multimodal","url":"https://github.com/facebookresearch/multimodal"},{"title":"lucidrains/CoCa-pytorch","url":"https://github.com/lucidrains/CoCa-pytorch"},{"title":"amitakamath/whatsup_vlms","url":"https://github.com/amitakamath/whatsup_vlms"},{"title":"amitakamath/hard_positives","url":"https://github.com/amitakamath/hard_positives"},{"title":"Chaolei98/FreeZAD","url":"https://github.com/Chaolei98/FreeZAD"}],"metrics_order":"[\"Accuracy (Private)\", \"Accuracy (Public)\", \"Top 5 Accuracy\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":113233,"task":"Zero-Shot Transfer Image Classification","parent_task":null,"dataset":"ObjectNet","model_name":"EVA-CLIP-18B","metrics":{"Accuracy (Private)":"82.2"},"paper_url":"https://arxiv.org/abs/2402.04252v1","paper_title":"EVA-CLIP-18B: Scaling CLIP to 18 Billion Parameters","paper_date":"2024-02-06","code_links":[{"title":"baaivision/EVA","url":"https://github.com/baaivision/EVA/tree/master/EVA-CLIP-18B"},{"title":"baaivision/eva","url":"https://github.com/baaivision/eva"}],"metrics_order":"[\"Accuracy (Private)\", \"Accuracy (Public)\", \"Top 5 Accuracy\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":113234,"task":"Zero-Shot Transfer Image Classification","parent_task":null,"dataset":"ObjectNet","model_name":"LiT-tuning","metrics":{"Accuracy (Private)":"81.1","Accuracy (Public)":" 54.5"},"paper_url":"https://arxiv.org/abs/2111.07991v3","paper_title":"LiT: Zero-Shot Transfer with Locked-image text Tuning","paper_date":"2021-11-15","code_links":[{"title":"mlfoundations/open_clip","url":"https://github.com/mlfoundations/open_clip"},{"title":"google-research/vision_transformer","url":"https://github.com/google-research/vision_transformer"},{"title":"google-research/big_vision","url":"https://github.com/google-research/big_vision"},{"title":"laion-ai/clip_benchmark","url":"https://github.com/laion-ai/clip_benchmark"},{"title":"eify/clip_benchmark","url":"https://github.com/eify/clip_benchmark"}],"metrics_order":"[\"Accuracy (Private)\", \"Accuracy (Public)\", \"Top 5 Accuracy\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":113235,"task":"Zero-Shot Transfer Image Classification","parent_task":null,"dataset":"ObjectNet","model_name":"InternVL-C","metrics":{"Accuracy (Private)":"80.6"},"paper_url":"https://arxiv.org/abs/2312.14238v3","paper_title":"InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks","paper_date":"2023-12-21","code_links":[{"title":"opengvlab/internvl","url":"https://github.com/opengvlab/internvl"},{"title":"opengvlab/internvl-mmdetseg","url":"https://github.com/opengvlab/internvl-mmdetseg"}],"metrics_order":"[\"Accuracy (Private)\", \"Accuracy (Public)\", \"Top 5 Accuracy\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":113236,"task":"Zero-Shot Transfer Image Classification","parent_task":null,"dataset":"ObjectNet","model_name":"EVA-CLIP-E/14+","metrics":{"Accuracy (Private)":"79.6"},"paper_url":"https://arxiv.org/abs/2303.15389v1","paper_title":"EVA-CLIP: Improved Training Techniques for CLIP at Scale","paper_date":"2023-03-27","code_links":[{"title":"baaivision/eva","url":"https://github.com/baaivision/eva"},{"title":"PaddlePaddle/PaddleMIX","url":"https://github.com/PaddlePaddle/PaddleMIX/tree/develop/paddlemix/examples"},{"title":"Yui010206/CREMA","url":"https://github.com/Yui010206/CREMA"},{"title":"jaehong31/raccoon","url":"https://github.com/jaehong31/raccoon"}],"metrics_order":"[\"Accuracy (Private)\", \"Accuracy (Public)\", \"Top 5 Accuracy\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":113237,"task":"Zero-Shot Transfer Image Classification","parent_task":null,"dataset":"ObjectNet","model_name":"CLIP","metrics":{"Accuracy (Private)":"72.3","Accuracy (Public)":"-"},"paper_url":"https://arxiv.org/abs/2103.00020v1","paper_title":"Learning Transferable Visual Models From Natural Language Supervision","paper_date":"2021-02-26","code_links":[{"title":"openai/CLIP","url":"https://github.com/openai/CLIP"},{"title":"mlfoundations/open_clip","url":"https://github.com/mlfoundations/open_clip"},{"title":"towhee-io/towhee","url":"https://github.com/towhee-io/towhee"},{"title":"facebookresearch/vissl","url":"https://github.com/facebookresearch/vissl"},{"title":"alibaba/EasyNLP","url":"https://github.com/alibaba/EasyNLP"},{"title":"apple/ml-mobileclip","url":"https://github.com/apple/ml-mobileclip"},{"title":"OML-Team/open-metric-learning","url":"https://github.com/OML-Team/open-metric-learning"},{"title":"FreddeFrallan/Multilingual-CLIP","url":"https://github.com/FreddeFrallan/Multilingual-CLIP"},{"title":"eps696/aphantasia","url":"https://github.com/eps696/aphantasia"},{"title":"muzairkhattak/multimodal-prompt-learning","url":"https://github.com/muzairkhattak/multimodal-prompt-learning"},{"title":"moein-shariatnia/OpenAI-CLIP","url":"https://github.com/moein-shariatnia/OpenAI-CLIP"},{"title":"facebookresearch/brainmagick","url":"https://github.com/facebookresearch/brainmagick"},{"title":"PaddlePaddle/PASSL","url":"https://github.com/PaddlePaddle/PASSL/blob/main/docs/Train_CLIP_model.md"},{"title":"taited/clip-score","url":"https://github.com/taited/clip-score"},{"title":"azshue/TPT","url":"https://github.com/azshue/TPT"},{"title":"clip-italian/clip-italian","url":"https://github.com/clip-italian/clip-italian"},{"title":"dhansmair/flamingo-mini","url":"https://github.com/dhansmair/flamingo-mini"},{"title":"ylqi/count-anything","url":"https://github.com/ylqi/count-anything"},{"title":"ml-jku/cloob","url":"https://github.com/ml-jku/cloob"},{"title":"sberbank-ai/ru-clip","url":"https://github.com/sberbank-ai/ru-clip"},{"title":"ai-forever/ru-clip","url":"https://github.com/ai-forever/ru-clip"},{"title":"Kaushalya/medclip","url":"https://github.com/Kaushalya/medclip"},{"title":"ajayjain/vectorascent","url":"https://github.com/ajayjain/vectorascent"},{"title":"linjieli222/hero_video_feature_extractor","url":"https://github.com/linjieli222/hero_video_feature_extractor"},{"title":"borisdayma/clip-jax","url":"https://github.com/borisdayma/clip-jax"},{"title":"sajjjadayobi/CLIPfa","url":"https://github.com/sajjjadayobi/CLIPfa"},{"title":"mertyg/post-hoc-cbm","url":"https://github.com/mertyg/post-hoc-cbm"},{"title":"mlbio-epfl/turtle","url":"https://github.com/mlbio-epfl/turtle"},{"title":"rinnakk/japanese-clip","url":"https://github.com/rinnakk/japanese-clip"},{"title":"salesforce/pb-ovd","url":"https://github.com/salesforce/pb-ovd"},{"title":"facebookresearch/clip-rocket","url":"https://github.com/facebookresearch/clip-rocket"},{"title":"sincerass/mvlpt","url":"https://github.com/sincerass/mvlpt"},{"title":"ericyinyzy/vlattack","url":"https://github.com/ericyinyzy/vlattack"},{"title":"redcaps-dataset/redcaps-downloader","url":"https://github.com/redcaps-dataset/redcaps-downloader"},{"title":"bespontaneous/proteus-pytorch","url":"https://github.com/bespontaneous/proteus-pytorch"},{"title":"shunk031/simple-aesthetics-predictor","url":"https://github.com/shunk031/simple-aesthetics-predictor"},{"title":"giantseaweed/decree","url":"https://github.com/giantseaweed/decree"},{"title":"sithu31296/simple-object-tracking","url":"https://github.com/sithu31296/simple-object-tracking"},{"title":"Gahyeonkim09/AAPL","url":"https://github.com/Gahyeonkim09/AAPL"},{"title":"filipbasara0/simple-clip","url":"https://github.com/filipbasara0/simple-clip"},{"title":"michi-3000/eyeclip","url":"https://github.com/michi-3000/eyeclip"},{"title":"baskargroup/Arboretum","url":"https://github.com/baskargroup/Arboretum"},{"title":"baskargroup/biotrove","url":"https://github.com/baskargroup/biotrove"},{"title":"kynkaat/role-of-imagenet-classes-in-fid","url":"https://github.com/kynkaat/role-of-imagenet-classes-in-fid"},{"title":"SforAiDl/CountCLIP","url":"https://github.com/SforAiDl/CountCLIP"},{"title":"mainaksingha01/applenet","url":"https://github.com/mainaksingha01/applenet"},{"title":"zhangxu0963/npc","url":"https://github.com/zhangxu0963/npc"},{"title":"mainaksingha01/odg-clip","url":"https://github.com/mainaksingha01/odg-clip"},{"title":"jhaprince/multibully","url":"https://github.com/jhaprince/multibully"},{"title":"klemens-floege/oneprot","url":"https://github.com/klemens-floege/oneprot"},{"title":"leolee99/CLIP_ITM","url":"https://github.com/leolee99/CLIP_ITM"},{"title":"madrylab/pretraining-distribution-shift-robustness","url":"https://github.com/madrylab/pretraining-distribution-shift-robustness"},{"title":"AndresPMD/Clip_CMR","url":"https://github.com/AndresPMD/Clip_CMR"},{"title":"fastscience-ai/medflamingo","url":"https://github.com/fastscience-ai/medflamingo"},{"title":"buyeah1109/KEN","url":"https://github.com/buyeah1109/KEN"},{"title":"pseulki/rococo","url":"https://github.com/pseulki/rococo"},{"title":"shkarupa-alex/tfclip","url":"https://github.com/shkarupa-alex/tfclip"},{"title":"IMvision12/keras-vision-models","url":"https://github.com/IMvision12/keras-vision-models"},{"title":"brown-palm/ObjectPrompt","url":"https://github.com/brown-palm/ObjectPrompt"},{"title":"YvanG/VQGAN-CLIP","url":"https://github.com/YvanG/VQGAN-CLIP"},{"title":"ramanakshay/clip","url":"https://github.com/ramanakshay/clip"},{"title":"NYU-DICE-Lab/open_clip","url":"https://github.com/NYU-DICE-Lab/open_clip"},{"title":"shivammehta25/clip","url":"https://github.com/shivammehta25/clip"},{"title":"minhanh151/respro","url":"https://github.com/minhanh151/respro"},{"title":"nopperl/clip_arxiv_pmc","url":"https://github.com/nopperl/clip_arxiv_pmc"},{"title":"s-a-malik/multi-few","url":"https://github.com/s-a-malik/multi-few"},{"title":"prabhupad26/100daysofML","url":"https://github.com/prabhupad26/100daysofML"},{"title":"armaank/archlectures","url":"https://github.com/armaank/archlectures"},{"title":"minhanh151/pre","url":"https://github.com/minhanh151/pre"},{"title":"yuuun/clip_pytorch","url":"https://github.com/yuuun/clip_pytorch"},{"title":"2024-MindSpore-1/Code2","url":"https://github.com/2024-MindSpore-1/Code2/tree/main/model-1/clip"},{"title":"lunaproject22/rpa","url":"https://github.com/lunaproject22/rpa"},{"title":"fiabdu/Commonly-Interesting-Images","url":"https://github.com/fiabdu/Commonly-Interesting-Images"},{"title":"iejMac/ScriptWriter","url":"https://github.com/iejMac/ScriptWriter"},{"title":"ZackPashkin/text2cartoon-pytorch-CLIP","url":"https://github.com/ZackPashkin/text2cartoon-pytorch-CLIP"},{"title":"bruthyu/bpt-vlm","url":"https://github.com/bruthyu/bpt-vlm"},{"title":"buyeah1109/finc","url":"https://github.com/buyeah1109/finc"},{"title":"pwc-1/Paper-8","url":"https://github.com/pwc-1/Paper-8/tree/main/clip"},{"title":"eify/open_clip","url":"https://github.com/eify/open_clip"},{"title":"2023-MindSpore-4/Code12","url":"https://github.com/2023-MindSpore-4/Code12/tree/main/MindFormers/clip"},{"title":"a736875071/clip-vit-large-patch14","url":"https://github.com/a736875071/clip-vit-large-patch14"},{"title":"nahidalam/open_clip","url":"https://github.com/nahidalam/open_clip"}],"metrics_order":"[\"Accuracy (Private)\", \"Accuracy (Public)\", \"Top 5 Accuracy\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":113238,"task":"Zero-Shot Transfer Image Classification","parent_task":null,"dataset":"ObjectNet","model_name":"PaLI","metrics":{"Accuracy (Private)":"42.62","Top 5 Accuracy":"58.35"},"paper_url":"https://arxiv.org/abs/2209.06794v4","paper_title":"PaLI: A Jointly-Scaled Multilingual Language-Image Model","paper_date":"2022-09-14","code_links":[{"title":"google-research/big_vision","url":"https://github.com/google-research/big_vision"}],"metrics_order":"[\"Accuracy (Private)\", \"Accuracy (Public)\", \"Top 5 Accuracy\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]}]}