{"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/zoomnext-a-unified-collaborative-pyramid","title":"ZoomNeXt: A Unified Collaborative Pyramid Network for Camouflaged Object Detection","arxiv_id":"2310.20208","date":"2023-10-31","proceeding":null,"authors":["Youwei Pang","Xiaoqi Zhao","Tian-Zhu Xiang","Lihe Zhang","Huchuan Lu"],"abstract":"Recent camouflaged object detection (COD) attempts to segment objects visually blended into their surroundings, which is extremely complex and difficult in real-world scenarios. Apart from the high intrinsic similarity between camouflaged objects and their background, objects are usually diverse in scale, fuzzy in appearance, and even severely occluded. To this end, we propose an effective unified collaborative pyramid network that mimics human behavior when observing vague images and videos, \\ie zooming in and out. Specifically, our approach employs the zooming strategy to learn discriminative mixed-scale semantics by the multi-head scale integration and rich granularity perception units, which are designed to fully explore imperceptible clues between candidate objects and background surroundings. The former's intrinsic multi-head aggregation provides more diverse visual patterns. The latter's routing mechanism can effectively propagate inter-frame differences in spatiotemporal scenarios and be adaptively deactivated and output all-zero results for static representations. They provide a solid foundation for realizing a unified architecture for static and dynamic COD. Moreover, considering the uncertainty and ambiguity derived from indistinguishable textures, we construct a simple yet effective regularization, uncertainty awareness loss, to encourage predictions with higher confidence in candidate regions. Our highly task-friendly framework consistently outperforms existing state-of-the-art methods in image and video COD benchmarks. Our code can be found at {https://github.com/lartpang/ZoomNeXt}.","url_abs":"https://arxiv.org/abs/2310.20208v4","url_pdf":"https://arxiv.org/pdf/2310.20208v4.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":"zoomnext-a-unified-collaborative-pyramid","repo_url":"https://github.com/lartpang/zoomnext","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"camouflaged-object-segmentation","task_name":"Camouflaged Object Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/camouflaged-object-segmentation-on-camo","task":"Camouflaged Object Segmentation","dataset":"CAMO","model":"ZoomNeXt-PVTv2-B5","rank_in_archive_order":3,"of":14,"metrics":{"MAE":"0.041","S-Measure":"0.889","Weighted F-Measure":"0.857"},"uses_additional_data":false},{"leaderboard":"/sota/camouflaged-object-segmentation-on-camo","task":"Camouflaged Object Segmentation","dataset":"CAMO","model":"ZoomNeXt-PVTv2-B4","rank_in_archive_order":4,"of":14,"metrics":{"MAE":"0.04","S-Measure":"0.888","Weighted F-Measure":"0.859"},"uses_additional_data":false},{"leaderboard":"/sota/camouflaged-object-segmentation-on-camo","task":"Camouflaged Object Segmentation","dataset":"CAMO","model":"ZoomNeXt-ResNet-50","rank_in_archive_order":7,"of":14,"metrics":{"MAE":"0.065","S-Measure":"0.833","Weighted F-Measure":"0.774"},"uses_additional_data":false},{"leaderboard":"/sota/camouflaged-object-segmentation-on-chameleon","task":"Camouflaged Object Segmentation","dataset":"CHAMELEON","model":"ZoomNeXt-PVTv2-B4","rank_in_archive_order":2,"of":6,"metrics":{"MAE":"0.016","S-measure":"0.925","weighted F-measure":"0.897"},"uses_additional_data":false},{"leaderboard":"/sota/camouflaged-object-segmentation-on-chameleon","task":"Camouflaged Object Segmentation","dataset":"CHAMELEON","model":"ZoomNeXt-PVTv2-B5","rank_in_archive_order":3,"of":6,"metrics":{"MAE":"0.018","S-measure":"0.924","weighted F-measure":"0.885"},"uses_additional_data":false},{"leaderboard":"/sota/camouflaged-object-segmentation-on-chameleon","task":"Camouflaged Object Segmentation","dataset":"CHAMELEON","model":"ZoomNeXt-ResNet-50","rank_in_archive_order":5,"of":6,"metrics":{"MAE":"0.021","S-measure":"0.908","weighted F-measure":"0.858"},"uses_additional_data":false},{"leaderboard":"/sota/camouflaged-object-segmentation-on-cod","task":"Camouflaged Object Segmentation","dataset":"COD","model":"ZoomNeXt-PVTv2-B4","rank_in_archive_order":3,"of":12,"metrics":{"MAE":"0.017","S-Measure":"0.898","Weighted F-Measure":"0.838"},"uses_additional_data":false},{"leaderboard":"/sota/camouflaged-object-segmentation-on-cod","task":"Camouflaged Object Segmentation","dataset":"COD","model":"ZoomNeXt-PVTv2-B5","rank_in_archive_order":4,"of":12,"metrics":{"MAE":"0.018","S-Measure":"0.898","Weighted F-Measure":"0.827"},"uses_additional_data":false},{"leaderboard":"/sota/camouflaged-object-segmentation-on-cod","task":"Camouflaged Object Segmentation","dataset":"COD","model":"ZoomNeXt-ResNet-50","rank_in_archive_order":5,"of":12,"metrics":{"MAE":"0.026","S-Measure":"0.861","Weighted F-Measure":"0.768"},"uses_additional_data":false},{"leaderboard":"/sota/camouflaged-object-segmentation-on","task":"Camouflaged Object Segmentation","dataset":"Camouflaged Animal Dataset","model":"ZoomNeXt-PVTv2-B5","rank_in_archive_order":1,"of":2,"metrics":{"MAE":"0.020","S-measure":"0.757","mDice":"0.599","mIoU":"0.510","weighted F-measure":"0.593"},"uses_additional_data":true},{"leaderboard":"/sota/camouflaged-object-segmentation-on-moca-mask","task":"Camouflaged Object Segmentation","dataset":"MoCA-Mask","model":"ZoomNeXt-PVTv2-B5","rank_in_archive_order":3,"of":4,"metrics":{"MAE":"0.010","S-measure":"0.734","mDice":"0.497","mIoU":"0.422","weighted F-measure":"0.476"},"uses_additional_data":true},{"leaderboard":"/sota/camouflaged-object-segmentation-on-nc4k","task":"Camouflaged Object Segmentation","dataset":"NC4K","model":"ZoomNeXt-PVTv2-B5","rank_in_archive_order":3,"of":6,"metrics":{"MAE":"0.028","S-measure":"0.903","weighted F-measure":"0.863"},"uses_additional_data":false},{"leaderboard":"/sota/camouflaged-object-segmentation-on-nc4k","task":"Camouflaged Object Segmentation","dataset":"NC4K","model":"ZoomNeXt-PVTv2-B4","rank_in_archive_order":4,"of":6,"metrics":{"MAE":"0.028","S-measure":"0.900","weighted F-measure":"0.865"},"uses_additional_data":false},{"leaderboard":"/sota/camouflaged-object-segmentation-on-nc4k","task":"Camouflaged Object Segmentation","dataset":"NC4K","model":"ZoomNeXt-ResNet-50","rank_in_archive_order":5,"of":6,"metrics":{"MAE":"0.037","S-measure":"0.874","weighted F-measure":"0.816"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2310.20208","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.20208"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/lartpang/zoomnext","reach":{"status":"ok"}}],"summary":{"ran_fixture":1,"ran":5,"ran_draft_wrong":2,"unverified":3},"by_repo_kind":{"official":{"samples":11,"ran":8,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":11,"samples":[{"code_sha256_prefix":"d3319e3d34ca90ca","entry":"drop_connect","repo":"lartpang/zoomnext","repo_kind":"official","path":"methods/backbone/efficientnet_utils.py","file_url":"https://github.com/lartpang/zoomnext/blob/HEAD/methods/backbone/efficientnet_utils.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d3319e3d34ca90ca"}},{"code_sha256_prefix":"9e7dc78e212b35c6","entry":"get_number_from_tail","repo":"lartpang/zoomnext","repo_kind":"official","path":"main_for_video.py","file_url":"https://github.com/lartpang/zoomnext/blob/HEAD/main_for_video.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9e7dc78e212b35c6"}},{"code_sha256_prefix":"a5515f1fc979e6d6","entry":"global_avgpool","repo":"lartpang/zoomnext","repo_kind":"official","path":"methods/zoomnext/ops.py","file_url":"https://github.com/lartpang/zoomnext/blob/HEAD/methods/zoomnext/ops.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a5515f1fc979e6d6"}},{"code_sha256_prefix":"50dd0948aed10a9f","entry":"rescale_2x","repo":"lartpang/zoomnext","repo_kind":"official","path":"methods/zoomnext/ops.py","file_url":"https://github.com/lartpang/zoomnext/blob/HEAD/methods/zoomnext/ops.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"50dd0948aed10a9f"}},{"code_sha256_prefix":"6c1c631c1b7d59f6","entry":"resize_to","repo":"lartpang/zoomnext","repo_kind":"official","path":"methods/zoomnext/ops.py","file_url":"https://github.com/lartpang/zoomnext/blob/HEAD/methods/zoomnext/ops.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6c1c631c1b7d59f6"}},{"code_sha256_prefix":"f15a49337e69e937","entry":"round_filters","repo":"lartpang/zoomnext","repo_kind":"official","path":"methods/backbone/efficientnet_utils.py","file_url":"https://github.com/lartpang/zoomnext/blob/HEAD/methods/backbone/efficientnet_utils.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f15a49337e69e937"}},{"code_sha256_prefix":"dbc0ca08d119a5a0","entry":"round_repeats","repo":"lartpang/zoomnext","repo_kind":"official","path":"methods/backbone/efficientnet_utils.py","file_url":"https://github.com/lartpang/zoomnext/blob/HEAD/methods/backbone/efficientnet_utils.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"dbc0ca08d119a5a0"}},{"code_sha256_prefix":"1ba3a66aa94bcd70","entry":"to_device","repo":"lartpang/zoomnext","repo_kind":"official","path":"utils/pt_utils.py","file_url":"https://github.com/lartpang/zoomnext/blob/HEAD/utils/pt_utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1ba3a66aa94bcd70"}},{"code_sha256_prefix":"50afc7a23013128c","entry":"pvt_v2_eff_b0","repo":"lartpang/zoomnext","repo_kind":"official","path":"methods/backbone/pvt_v2_eff.py","file_url":"https://github.com/lartpang/zoomnext/blob/HEAD/methods/backbone/pvt_v2_eff.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"50afc7a23013128c"}},{"code_sha256_prefix":"c2a13fa3d074c9b8","entry":"pvt_v2_eff_b1","repo":"lartpang/zoomnext","repo_kind":"official","path":"methods/backbone/pvt_v2_eff.py","file_url":"https://github.com/lartpang/zoomnext/blob/HEAD/methods/backbone/pvt_v2_eff.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c2a13fa3d074c9b8"}},{"code_sha256_prefix":"a134d3f57176aaa7","entry":"pvt_v2_eff_b2","repo":"lartpang/zoomnext","repo_kind":"official","path":"methods/backbone/pvt_v2_eff.py","file_url":"https://github.com/lartpang/zoomnext/blob/HEAD/methods/backbone/pvt_v2_eff.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a134d3f57176aaa7"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}