{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/instanceformer-an-online-video-instance","title":"InstanceFormer: An Online Video Instance Segmentation Framework","arxiv_id":"2208.10547","date":"2022-08-22","proceeding":null,"authors":["Rajat Koner","Tanveer Hannan","Suprosanna Shit","Sahand Sharifzadeh","Matthias Schubert","Thomas Seidl","Volker Tresp"],"abstract":"Recent transformer-based offline video instance segmentation (VIS) approaches achieve encouraging results and significantly outperform online approaches. However, their reliance on the whole video and the immense computational complexity caused by full Spatio-temporal attention limit them in real-life applications such as processing lengthy videos. In this paper, we propose a single-stage transformer-based efficient online VIS framework named InstanceFormer, which is especially suitable for long and challenging videos. We propose three novel components to model short-term and long-term dependency and temporal coherence. First, we propagate the representation, location, and semantic information of prior instances to model short-term changes. Second, we propose a novel memory cross-attention in the decoder, which allows the network to look into earlier instances within a certain temporal window. Finally, we employ a temporal contrastive loss to impose coherence in the representation of an instance across all frames. Memory attention and temporal coherence are particularly beneficial to long-range dependency modeling, including challenging scenarios like occlusion. The proposed InstanceFormer outperforms previous online benchmark methods by a large margin across multiple datasets. Most importantly, InstanceFormer surpasses offline approaches for challenging and long datasets such as YouTube-VIS-2021 and OVIS. Code is available at https://github.com/rajatkoner08/InstanceFormer.","url_abs":"https://arxiv.org/abs/2208.10547v1","url_pdf":"https://arxiv.org/pdf/2208.10547v1.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":"instanceformer-an-online-video-instance","repo_url":"https://github.com/rajatkoner08/instanceformer","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"instance-segmentation","task_name":"Instance Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"video-instance-segmentation","task_name":"Video Instance Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/video-instance-segmentation-on-ovis-1","task":"Video Instance Segmentation","dataset":"OVIS validation","model":"InstanceFormer (Swin-L)","rank_in_archive_order":34,"of":44,"metrics":{"AP50":"42.5","AP75":"21.61","AR1":"12.9","AR10":"29.3","mask AP":"22.8"},"uses_additional_data":true},{"leaderboard":"/sota/video-instance-segmentation-on-ovis-1","task":"Video Instance Segmentation","dataset":"OVIS validation","model":"InstanceFormer(ResNet-50)","rank_in_archive_order":35,"of":44,"metrics":{"AP50":"40.7","AP75":"18.1","AR1":"12","AR10":"27.1","mask AP":"20.0"},"uses_additional_data":true},{"leaderboard":"/sota/video-instance-segmentation-on-youtube-vis-2","task":"Video Instance Segmentation","dataset":"YouTube-VIS 2021","model":"InstanceFormer (Swin-L)","rank_in_archive_order":19,"of":26,"metrics":{"AP50":"73.7","AP75":"56.9","AR1":"42.8","AR10":"56.0","mask AP":"51.0"},"uses_additional_data":true},{"leaderboard":"/sota/video-instance-segmentation-on-youtube-vis-2","task":"Video Instance Segmentation","dataset":"YouTube-VIS 2021","model":"InstanceFormer  (ResNet-50)","rank_in_archive_order":25,"of":26,"metrics":{"AP50":"62.4","AP75":"43.7","AR1":"36.1","AR10":"48.1","mask AP":"40.8"},"uses_additional_data":true},{"leaderboard":"/sota/video-instance-segmentation-on-youtube-vis-1","task":"Video Instance Segmentation","dataset":"YouTube-VIS validation","model":"InstanceFormer(Swin-L)","rank_in_archive_order":11,"of":44,"metrics":{"AP50":"78.0","AP75":"64.2","AR1":"50.9","AR10":"61.6","mask AP":"56.3"},"uses_additional_data":true},{"leaderboard":"/sota/video-instance-segmentation-on-youtube-vis-1","task":"Video Instance Segmentation","dataset":"YouTube-VIS validation","model":"InstanceFormer(ResNet-50)","rank_in_archive_order":21,"of":44,"metrics":{"AP50":"68.6","AP75":"49.6","AR1":"42.1","AR10":"53.5","mask AP":"45.6"},"uses_additional_data":true},{"leaderboard":"/sota/video-instance-segmentation-on-youtube-vis-3","task":"Video Instance Segmentation","dataset":"Youtube-VIS 2022 Validation","model":"InstanceFormer (Swin)","rank_in_archive_order":6,"of":7,"metrics":{"AP50_L":"44.6","AP75_L":"27.3","AR10_L":"29.2","AR1_L":"25.0","mAP_L":"26.3"},"uses_additional_data":true},{"leaderboard":"/sota/video-instance-segmentation-on-youtube-vis-3","task":"Video Instance Segmentation","dataset":"Youtube-VIS 2022 Validation","model":"InstanceFormer (Resnet-50)","rank_in_archive_order":7,"of":7,"metrics":{"AP50_L":"49.5","AP75_L":"26.7","AR10_L":"30.1","AR1_L":"23.9","mAP_L":"24.8"},"uses_additional_data":true}],"syntology":{"syntology_url":"https://syntology.ai/paper/2208.10547","atlas_url":"https://app.syntology.ai/?focus=2208.10547","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2208.10547"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2208.10547\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2208.10547"},"call":"get_concepts_for_paper(arxiv_id=\"2208.10547\")"}],"by_repo":[{"repo":"rajatkoner08/instanceformer","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["aaai_25201"],"harvested_for_calls":[]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"80185a62baba688b2c29f55f767e65a401e1362e5d9e9628b55f7b28661509c0","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}