{"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/instance-segmentation-by-jointly-optimizing-1","title":"Instance Segmentation by Jointly Optimizing Spatial Embeddings and Clustering Bandwidth","arxiv_id":"1906.11109","date":"2019-06-26","proceeding":"CVPR 2019 6","authors":["Davy Neven","Bert de Brabandere","Marc Proesmans","Luc van Gool"],"abstract":"Current state-of-the-art instance segmentation methods are not suited for real-time applications like autonomous driving, which require fast execution times at high accuracy. Although the currently dominant proposal-based methods have high accuracy, they are slow and generate masks at a fixed and low resolution. Proposal-free methods, by contrast, can generate masks at high resolution and are often faster, but fail to reach the same accuracy as the proposal-based methods. In this work we propose a new clustering loss function for proposal-free instance segmentation. The loss function pulls the spatial embeddings of pixels belonging to the same instance together and jointly learns an instance-specific clustering bandwidth, maximizing the intersection-over-union of the resulting instance mask. When combined with a fast architecture, the network can perform instance segmentation in real-time while maintaining a high accuracy. We evaluate our method on the challenging Cityscapes benchmark and achieve top results (5\\% improvement over Mask R-CNN) at more than 10 fps on 2MP images. Code will be available at https://github.com/davyneven/SpatialEmbeddings .","url_abs":"https://arxiv.org/abs/1906.11109v2","url_pdf":"https://arxiv.org/pdf/1906.11109v2.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":"instance-segmentation-by-jointly-optimizing-1","repo_url":"https://github.com/davyneven/SpatialEmbeddings","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"instance-segmentation-by-jointly-optimizing-1","repo_url":"https://github.com/gymoon10/Instance-Segmentation-with-SpatialEmbedding-CA","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"instance-segmentation-by-jointly-optimizing-1","repo_url":"https://github.com/juglab/EmbedSeg","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"instance-segmentation-by-jointly-optimizing-1","repo_url":"https://github.com/JLrumberger/SpatialEmbeddingLoss","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"autonomous-driving","task_name":"Autonomous Driving"},{"task_slug":"clustering","task_name":"Clustering"},{"task_slug":"instance-segmentation","task_name":"Instance Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/instance-segmentation-on-cityscapes","task":"Instance Segmentation","dataset":"Cityscapes test","model":"Learnable Margin","rank_in_archive_order":5,"of":11,"metrics":{},"uses_additional_data":false},{"leaderboard":"/sota/instance-segmentation-on-cityscapes","task":"Instance Segmentation","dataset":"Cityscapes test","model":"Instance Segmentation by Jointly Optimizing Spatial Embeddings and Clustering Bandwidth","rank_in_archive_order":7,"of":11,"metrics":{},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1906.11109","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.11109"}},"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/JLrumberger/SpatialEmbeddingLoss","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/gymoon10/Instance-Segmentation-with-SpatialEmbedding-CA","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/davyneven/SpatialEmbeddings","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/juglab/EmbedSeg","reach":null}],"summary":{"ran_violates":2},"by_repo_kind":{"listed":{"samples":2,"ran":2,"repositories":2}},"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":2,"samples":[{"code_sha256_prefix":"ca2d2f269115fbcc","entry":"calculate_iou","repo":"gymoon10/Instance-Segmentation-with-SpatialEmbedding-CA","repo_kind":"listed","path":"src/criterions/my_loss_cvppp.py","file_url":"https://github.com/gymoon10/Instance-Segmentation-with-SpatialEmbedding-CA/blob/HEAD/src/criterions/my_loss_cvppp.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ca2d2f269115fbcc"}},{"code_sha256_prefix":"c6c044cb318580e9","entry":"round_up_8","repo":"juglab/EmbedSeg","repo_kind":"listed","path":"EmbedSeg/utils/preprocess_data.py","file_url":"https://github.com/juglab/EmbedSeg/blob/HEAD/EmbedSeg/utils/preprocess_data.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"c6c044cb318580e9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}