{"task":"Object Detection","dataset":"COCO (Common Objects in Context)","metric_names":["box AP","GFlops"],"rows":[{"id":61956,"task":"Object Detection","parent_task":null,"dataset":"COCO (Common Objects in Context)","model_name":"MOAT-3 22K+1K","metrics":{"box AP":"59.2"},"paper_url":"https://arxiv.org/abs/2210.01820v2","paper_title":"MOAT: Alternating Mobile Convolution and Attention Brings Strong Vision Models","paper_date":"2022-10-04","code_links":[{"title":"google-research/deeplab2","url":"https://github.com/google-research/deeplab2"},{"title":"RooKichenn/pytorch-MOAT","url":"https://github.com/RooKichenn/pytorch-MOAT"}],"metrics_order":"[\"box AP\", \"GFlops\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":61957,"task":"Object Detection","parent_task":null,"dataset":"COCO (Common Objects in Context)","model_name":"MOAT-2","metrics":{"box AP":"58.5"},"paper_url":"https://arxiv.org/abs/2210.01820v2","paper_title":"MOAT: Alternating Mobile Convolution and Attention Brings Strong Vision Models","paper_date":"2022-10-04","code_links":[{"title":"google-research/deeplab2","url":"https://github.com/google-research/deeplab2"},{"title":"RooKichenn/pytorch-MOAT","url":"https://github.com/RooKichenn/pytorch-MOAT"}],"metrics_order":"[\"box AP\", \"GFlops\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":61958,"task":"Object Detection","parent_task":null,"dataset":"COCO (Common Objects in Context)","model_name":"REGO-Deformable DETR-X101","metrics":{"GFlops":"434"},"paper_url":"https://arxiv.org/abs/2112.04632v2","paper_title":"Recurrent Glimpse-based Decoder for Detection with Transformer","paper_date":"2021-12-09","code_links":[{"title":"zhechen/deformable-detr-rego","url":"https://github.com/zhechen/deformable-detr-rego"}],"metrics_order":"[\"box AP\", \"GFlops\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":75935,"task":"Object Detection","parent_task":"3D","dataset":"COCO (Common Objects in Context)","model_name":"MOAT-3 22K+1K","metrics":{"box AP":"59.2"},"paper_url":"https://arxiv.org/abs/2210.01820v2","paper_title":"MOAT: Alternating Mobile Convolution and Attention Brings Strong Vision Models","paper_date":"2022-10-04","code_links":[{"title":"google-research/deeplab2","url":"https://github.com/google-research/deeplab2"},{"title":"RooKichenn/pytorch-MOAT","url":"https://github.com/RooKichenn/pytorch-MOAT"}],"metrics_order":"[\"box AP\", \"GFlops\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":75936,"task":"Object Detection","parent_task":"3D","dataset":"COCO (Common Objects in Context)","model_name":"MOAT-2","metrics":{"box AP":"58.5"},"paper_url":"https://arxiv.org/abs/2210.01820v2","paper_title":"MOAT: Alternating Mobile Convolution and Attention Brings Strong Vision Models","paper_date":"2022-10-04","code_links":[{"title":"google-research/deeplab2","url":"https://github.com/google-research/deeplab2"},{"title":"RooKichenn/pytorch-MOAT","url":"https://github.com/RooKichenn/pytorch-MOAT"}],"metrics_order":"[\"box AP\", \"GFlops\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":75937,"task":"Object Detection","parent_task":"3D","dataset":"COCO (Common Objects in Context)","model_name":"REGO-Deformable DETR-X101","metrics":{"GFlops":"434"},"paper_url":"https://arxiv.org/abs/2112.04632v2","paper_title":"Recurrent Glimpse-based Decoder for Detection with Transformer","paper_date":"2021-12-09","code_links":[{"title":"zhechen/deformable-detr-rego","url":"https://github.com/zhechen/deformable-detr-rego"}],"metrics_order":"[\"box AP\", \"GFlops\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":116462,"task":"Object Detection","parent_task":"2D Classification","dataset":"COCO (Common Objects in Context)","model_name":"MOAT-3 22K+1K","metrics":{"box AP":"59.2"},"paper_url":"https://arxiv.org/abs/2210.01820v2","paper_title":"MOAT: Alternating Mobile Convolution and Attention Brings Strong Vision Models","paper_date":"2022-10-04","code_links":[{"title":"google-research/deeplab2","url":"https://github.com/google-research/deeplab2"},{"title":"RooKichenn/pytorch-MOAT","url":"https://github.com/RooKichenn/pytorch-MOAT"}],"metrics_order":"[\"box AP\", \"GFlops\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":116463,"task":"Object Detection","parent_task":"2D Classification","dataset":"COCO (Common Objects in Context)","model_name":"MOAT-2","metrics":{"box AP":"58.5"},"paper_url":"https://arxiv.org/abs/2210.01820v2","paper_title":"MOAT: Alternating Mobile Convolution and Attention Brings Strong Vision Models","paper_date":"2022-10-04","code_links":[{"title":"google-research/deeplab2","url":"https://github.com/google-research/deeplab2"},{"title":"RooKichenn/pytorch-MOAT","url":"https://github.com/RooKichenn/pytorch-MOAT"}],"metrics_order":"[\"box AP\", \"GFlops\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":116464,"task":"Object Detection","parent_task":"2D Classification","dataset":"COCO (Common Objects in Context)","model_name":"REGO-Deformable DETR-X101","metrics":{"GFlops":"434"},"paper_url":"https://arxiv.org/abs/2112.04632v2","paper_title":"Recurrent Glimpse-based Decoder for Detection with Transformer","paper_date":"2021-12-09","code_links":[{"title":"zhechen/deformable-detr-rego","url":"https://github.com/zhechen/deformable-detr-rego"}],"metrics_order":"[\"box AP\", \"GFlops\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":123538,"task":"Object Detection","parent_task":"2D Object Detection","dataset":"COCO (Common Objects in Context)","model_name":"MOAT-3 22K+1K","metrics":{"box AP":"59.2"},"paper_url":"https://arxiv.org/abs/2210.01820v2","paper_title":"MOAT: Alternating Mobile Convolution and Attention Brings Strong Vision Models","paper_date":"2022-10-04","code_links":[{"title":"google-research/deeplab2","url":"https://github.com/google-research/deeplab2"},{"title":"RooKichenn/pytorch-MOAT","url":"https://github.com/RooKichenn/pytorch-MOAT"}],"metrics_order":"[\"box AP\", \"GFlops\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":123539,"task":"Object Detection","parent_task":"2D Object Detection","dataset":"COCO (Common Objects in Context)","model_name":"MOAT-2","metrics":{"box AP":"58.5"},"paper_url":"https://arxiv.org/abs/2210.01820v2","paper_title":"MOAT: Alternating Mobile Convolution and Attention Brings Strong Vision Models","paper_date":"2022-10-04","code_links":[{"title":"google-research/deeplab2","url":"https://github.com/google-research/deeplab2"},{"title":"RooKichenn/pytorch-MOAT","url":"https://github.com/RooKichenn/pytorch-MOAT"}],"metrics_order":"[\"box AP\", \"GFlops\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":123540,"task":"Object Detection","parent_task":"2D Object Detection","dataset":"COCO (Common Objects in Context)","model_name":"REGO-Deformable DETR-X101","metrics":{"GFlops":"434"},"paper_url":"https://arxiv.org/abs/2112.04632v2","paper_title":"Recurrent Glimpse-based Decoder for Detection with Transformer","paper_date":"2021-12-09","code_links":[{"title":"zhechen/deformable-detr-rego","url":"https://github.com/zhechen/deformable-detr-rego"}],"metrics_order":"[\"box AP\", \"GFlops\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":149257,"task":"Object Detection","parent_task":"16k","dataset":"COCO (Common Objects in Context)","model_name":"MOAT-3 22K+1K","metrics":{"box AP":"59.2"},"paper_url":"https://arxiv.org/abs/2210.01820v2","paper_title":"MOAT: Alternating Mobile Convolution and Attention Brings Strong Vision Models","paper_date":"2022-10-04","code_links":[{"title":"google-research/deeplab2","url":"https://github.com/google-research/deeplab2"},{"title":"RooKichenn/pytorch-MOAT","url":"https://github.com/RooKichenn/pytorch-MOAT"}],"metrics_order":"[\"box AP\", \"GFlops\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":149258,"task":"Object Detection","parent_task":"16k","dataset":"COCO (Common Objects in Context)","model_name":"MOAT-2","metrics":{"box AP":"58.5"},"paper_url":"https://arxiv.org/abs/2210.01820v2","paper_title":"MOAT: Alternating Mobile Convolution and Attention Brings Strong Vision Models","paper_date":"2022-10-04","code_links":[{"title":"google-research/deeplab2","url":"https://github.com/google-research/deeplab2"},{"title":"RooKichenn/pytorch-MOAT","url":"https://github.com/RooKichenn/pytorch-MOAT"}],"metrics_order":"[\"box AP\", \"GFlops\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]},{"id":149259,"task":"Object Detection","parent_task":"16k","dataset":"COCO (Common Objects in Context)","model_name":"REGO-Deformable DETR-X101","metrics":{"GFlops":"434"},"paper_url":"https://arxiv.org/abs/2112.04632v2","paper_title":"Recurrent Glimpse-based Decoder for Detection with Transformer","paper_date":"2021-12-09","code_links":[{"title":"zhechen/deformable-detr-rego","url":"https://github.com/zhechen/deformable-detr-rego"}],"metrics_order":"[\"box AP\", \"GFlops\"]","area":"Computer Vision","uses_additional_data":0,"source":"archive","tags":[]}]}