{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/max-deeplab-end-to-end-panoptic-segmentation","title":"MaX-DeepLab: End-to-End Panoptic Segmentation with Mask Transformers","arxiv_id":"2012.00759","date":"2020-12-01","proceeding":"CVPR 2021 1","authors":["Huiyu Wang","Yukun Zhu","Hartwig Adam","Alan Yuille","Liang-Chieh Chen"],"abstract":"We present MaX-DeepLab, the first end-to-end model for panoptic segmentation. Our approach simplifies the current pipeline that depends heavily on surrogate sub-tasks and hand-designed components, such as box detection, non-maximum suppression, thing-stuff merging, etc. Although these sub-tasks are tackled by area experts, they fail to comprehensively solve the target task. By contrast, our MaX-DeepLab directly predicts class-labeled masks with a mask transformer, and is trained with a panoptic quality inspired loss via bipartite matching. Our mask transformer employs a dual-path architecture that introduces a global memory path in addition to a CNN path, allowing direct communication with any CNN layers. As a result, MaX-DeepLab shows a significant 7.1% PQ gain in the box-free regime on the challenging COCO dataset, closing the gap between box-based and box-free methods for the first time. A small variant of MaX-DeepLab improves 3.0% PQ over DETR with similar parameters and M-Adds. Furthermore, MaX-DeepLab, without test time augmentation, achieves new state-of-the-art 51.3% PQ on COCO test-dev set. Code is available at https://github.com/google-research/deeplab2.","url_abs":"https://arxiv.org/abs/2012.00759v3","url_pdf":"https://arxiv.org/pdf/2012.00759v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"max-deeplab-end-to-end-panoptic-segmentation","repo_url":"https://github.com/google-research/deeplab2","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"max-deeplab-end-to-end-panoptic-segmentation","repo_url":"https://github.com/bytedance/kmax-deeplab","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"max-deeplab-end-to-end-panoptic-segmentation","repo_url":"https://github.com/conradry/max-deeplab","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"panoptic-segmentation","task_name":"Panoptic Segmentation"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"detr","method_name":"Detr"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"feedforward-network","method_name":"Feedforward Network"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/panoptic-segmentation-on-coco-minival","task":"Panoptic Segmentation","dataset":"COCO minival","model":"MaX-DeepLab-L (single-scale)","rank_in_archive_order":22,"of":31,"metrics":{"PQ":"51.1","PQst":"42.2","PQth":"57.0"},"uses_additional_data":false},{"leaderboard":"/sota/panoptic-segmentation-on-coco-test-dev","task":"Panoptic Segmentation","dataset":"COCO test-dev","model":"MaX-DeepLab-L (single-scale)","rank_in_archive_order":12,"of":38,"metrics":{"PQ":"51.3","PQst":"42.4","PQth":"57.2"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2012.00759","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}