{"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/making-a-case-for-3d-convolutions-for-object","title":"Making a Case for 3D Convolutions for Object Segmentation in Videos","arxiv_id":"2008.11516","date":"2020-08-26","proceeding":null,"authors":["Sabarinath Mahadevan","Ali Athar","Aljoša Ošep","Sebastian Hennen","Laura Leal-Taixé","Bastian Leibe"],"abstract":"The task of object segmentation in videos is usually accomplished by processing appearance and motion information separately using standard 2D convolutional networks, followed by a learned fusion of the two sources of information. On the other hand, 3D convolutional networks have been successfully applied for video classification tasks, but have not been leveraged as effectively to problems involving dense per-pixel interpretation of videos compared to their 2D convolutional counterparts and lag behind the aforementioned networks in terms of performance. In this work, we show that 3D CNNs can be effectively applied to dense video prediction tasks such as salient object segmentation. We propose a simple yet effective encoder-decoder network architecture consisting entirely of 3D convolutions that can be trained end-to-end using a standard cross-entropy loss. To this end, we leverage an efficient 3D encoder, and propose a 3D decoder architecture, that comprises novel 3D Global Convolution layers and 3D Refinement modules. Our approach outperforms existing state-of-the-arts by a large margin on the DAVIS'16 Unsupervised, FBMS and ViSal dataset benchmarks in addition to being faster, thus showing that our architecture can efficiently learn expressive spatio-temporal features and produce high quality video segmentation masks. We have made our code and trained models publicly available at https://github.com/sabarim/3DC-Seg.","url_abs":"https://arxiv.org/abs/2008.11516v2","url_pdf":"https://arxiv.org/pdf/2008.11516v2.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":"making-a-case-for-3d-convolutions-for-object","repo_url":"https://github.com/sabarim/3DC-Seg","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"unsupervised-video-object-segmentation","task_name":"Unsupervised Video Object Segmentation"},{"task_slug":"video-classification","task_name":"Video Classification"},{"task_slug":"video-object-segmentation","task_name":"Video Object Segmentation"},{"task_slug":"video-prediction","task_name":"Video Prediction"},{"task_slug":"video-segmentation","task_name":"Video Segmentation"},{"task_slug":"video-semantic-segmentation","task_name":"Video Semantic Segmentation"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/unsupervised-video-object-segmentation-on-10","task":"Unsupervised Video Object Segmentation","dataset":"DAVIS 2016 val","model":"3DC-Seg","rank_in_archive_order":15,"of":25,"metrics":{"F":"84.7","G":"84.5","J":"84.3"},"uses_additional_data":false},{"leaderboard":"/sota/video-object-segmentation-on-davis-2016","task":"Video Object Segmentation","dataset":"DAVIS 2016","model":"3DC-Seg","rank_in_archive_order":18,"of":24,"metrics":{"F-Score":"84.7","Jaccard (Mean)":"84.3"},"uses_additional_data":true}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2008.11516","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2008.11516"}},"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/sabarim/3DC-Seg","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":3,"unverified":6},"by_repo_kind":{"official":{"samples":9,"ran":3,"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":0,"samples":[{"code_sha256_prefix":"c3b215555357b9d1","entry":"conv3x3x3","repo":"sabarim/3DC-Seg","repo_kind":"official","path":"network/Resnet3d.py","file_url":"https://github.com/sabarim/3DC-Seg/blob/HEAD/network/Resnet3d.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c3b215555357b9d1"}},{"code_sha256_prefix":"43c0211ff8dbca5f","entry":"downsample_basic_block","repo":"sabarim/3DC-Seg","repo_kind":"official","path":"network/Resnet3d.py","file_url":"https://github.com/sabarim/3DC-Seg/blob/HEAD/network/Resnet3d.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"43c0211ff8dbca5f"}},{"code_sha256_prefix":"8d57521c7b52b777","entry":"get_fine_tuning_parameters","repo":"sabarim/3DC-Seg","repo_kind":"official","path":"network/Resnet3d.py","file_url":"https://github.com/sabarim/3DC-Seg/blob/HEAD/network/Resnet3d.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8d57521c7b52b777"}},{"code_sha256_prefix":"3b84b83a1ad1cb0f","entry":"blobs_from_pkl","repo":"sabarim/3DC-Seg","repo_kind":"official","path":"network/convert_csn_weights.py","file_url":"https://github.com/sabarim/3DC-Seg/blob/HEAD/network/convert_csn_weights.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3b84b83a1ad1cb0f"}},{"code_sha256_prefix":"9e3beec0999a954f","entry":"bootstrapped_ce_loss","repo":"sabarim/3DC-Seg","repo_kind":"official","path":"loss/loss_utils.py","file_url":"https://github.com/sabarim/3DC-Seg/blob/HEAD/loss/loss_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9e3beec0999a954f"}},{"code_sha256_prefix":"d1494618265be1d5","entry":"calc_iou","repo":"sabarim/3DC-Seg","repo_kind":"official","path":"loss/loss_utils.py","file_url":"https://github.com/sabarim/3DC-Seg/blob/HEAD/loss/loss_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d1494618265be1d5"}},{"code_sha256_prefix":"9cb93dd46a39dbcd","entry":"propagate3d","repo":"sabarim/3DC-Seg","repo_kind":"official","path":"network/NetworkUtil.py","file_url":"https://github.com/sabarim/3DC-Seg/blob/HEAD/network/NetworkUtil.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9cb93dd46a39dbcd"}},{"code_sha256_prefix":"e227a1a6652f7f3d","entry":"r2plus1d_34","repo":"sabarim/3DC-Seg","repo_kind":"official","path":"network/R2plus1d.py","file_url":"https://github.com/sabarim/3DC-Seg/blob/HEAD/network/R2plus1d.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e227a1a6652f7f3d"}},{"code_sha256_prefix":"58780db97ad295fe","entry":"run_forward","repo":"sabarim/3DC-Seg","repo_kind":"official","path":"network/NetworkUtil.py","file_url":"https://github.com/sabarim/3DC-Seg/blob/HEAD/network/NetworkUtil.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"58780db97ad295fe"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}