{"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/panet-few-shot-image-semantic-segmentation","title":"PANet: Few-Shot Image Semantic Segmentation with Prototype Alignment","arxiv_id":"1908.06391","date":"2019-08-18","proceeding":"ICCV 2019 10","authors":["Kaixin Wang","Jun Hao Liew","Yingtian Zou","Daquan Zhou","Jiashi Feng"],"abstract":"Despite the great progress made by deep CNNs in image semantic segmentation, they typically require a large number of densely-annotated images for training and are difficult to generalize to unseen object categories. Few-shot segmentation has thus been developed to learn to perform segmentation from only a few annotated examples. In this paper, we tackle the challenging few-shot segmentation problem from a metric learning perspective and present PANet, a novel prototype alignment network to better utilize the information of the support set. Our PANet learns class-specific prototype representations from a few support images within an embedding space and then performs segmentation over the query images through matching each pixel to the learned prototypes. With non-parametric metric learning, PANet offers high-quality prototypes that are representative for each semantic class and meanwhile discriminative for different classes. Moreover, PANet introduces a prototype alignment regularization between support and query. With this, PANet fully exploits knowledge from the support and provides better generalization on few-shot segmentation. Significantly, our model achieves the mIoU score of 48.1% and 55.7% on PASCAL-5i for 1-shot and 5-shot settings respectively, surpassing the state-of-the-art method by 1.8% and 8.6%.","url_abs":"https://arxiv.org/abs/1908.06391v2","url_pdf":"https://arxiv.org/pdf/1908.06391v2.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":"panet-few-shot-image-semantic-segmentation","repo_url":"https://github.com/kaixin96/PANet","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"panet-few-shot-image-semantic-segmentation","repo_url":"https://github.com/CSCYQJ/LOCATION-SENSITIVE-LOCAL-PROTOTYPE-NETWORK","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"panet-few-shot-image-semantic-segmentation","repo_url":"https://github.com/LiheYoung/MiningFSS","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"panet-few-shot-image-semantic-segmentation","repo_url":"https://github.com/RogerQi/pascal-5i","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"panet-few-shot-image-semantic-segmentation","repo_url":"https://github.com/fanq15/ssp","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"few-shot-image-segmentation","task_name":"Few-Shot Semantic Segmentation"},{"task_slug":"metric-learning","task_name":"Metric Learning"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"adaptive-feature-pooling","method_name":"Adaptive Feature Pooling"},{"method_slug":"bottom-up-path-augmentation","method_name":"Bottom-up Path Augmentation"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"fpn","method_name":"FPN"},{"method_slug":"pafpn","method_name":"PAFPN"},{"method_slug":"panet","method_name":"PANet"},{"method_slug":"rpn","method_name":"RPN"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"roi-align","method_name":"RoIAlign"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/few-shot-semantic-segmentation-on-coco-20i-1","task":"Few-Shot Semantic Segmentation","dataset":"COCO-20i (1-shot)","model":"PANet (VGG-16)","rank_in_archive_order":84,"of":85,"metrics":{"FB-IoU":"59.2","Mean IoU":"20.9"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-semantic-segmentation-on-coco-20i-2-1","task":"Few-Shot Semantic Segmentation","dataset":"COCO-20i (2-way 1-shot)","model":"PANet (ResNet-50)","rank_in_archive_order":6,"of":6,"metrics":{"mIoU":"18.0"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-semantic-segmentation-on-coco-20i-5","task":"Few-Shot Semantic Segmentation","dataset":"COCO-20i (5-shot)","model":"PANet (VGG-16)","rank_in_archive_order":79,"of":81,"metrics":{"FB-IoU":"63.5","Mean IoU":"29.7"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-semantic-segmentation-on-pascal-5i-1","task":"Few-Shot Semantic Segmentation","dataset":"PASCAL-5i (1-Shot)","model":"PANet (VGG-16)","rank_in_archive_order":103,"of":105,"metrics":{"FB-IoU":"66.5","Mean IoU":"48.1"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-semantic-segmentation-on-pascal-5i-5","task":"Few-Shot Semantic Segmentation","dataset":"PASCAL-5i (5-Shot)","model":"PANet (VGG-16)","rank_in_archive_order":94,"of":96,"metrics":{"FB-IoU":"70.7","Mean IoU":"55.7"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1908.06391","atlas_url":"https://app.syntology.ai/?focus=1908.06391","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":"1908.06391"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1908.06391\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1908.06391"},"call":"get_concepts_for_paper(arxiv_id=\"1908.06391\")"}],"by_repo":[{"repo":"kaixin96/PANet","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"CSCYQJ/LOCATION-SENSITIVE-LOCAL-PROTOTYPE-NETWORK","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"LiheYoung/MiningFSS","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2103.15402"],"harvested_for_calls":[{"arxiv_id":"2103.15402","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2103.15402"},"call":"get_harvested_code_for_paper(arxiv_id=\"2103.15402\")"}]},{"repo":"RogerQi/pascal-5i","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"fanq15/ssp","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2207.11549"],"harvested_for_calls":[{"arxiv_id":"2207.11549","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2207.11549"},"call":"get_harvested_code_for_paper(arxiv_id=\"2207.11549\")"}]}],"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":"a95b2017a35c3208e913dc236c81673b81951f749e381c0849b12c1071be790e","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}