{"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/canet-class-agnostic-segmentation-networks","title":"CANet: Class-Agnostic Segmentation Networks with Iterative Refinement and Attentive Few-Shot Learning","arxiv_id":"1903.02351","date":"2019-03-06","proceeding":"CVPR 2019 6","authors":["Chi Zhang","Guosheng Lin","Fayao Liu","Rui Yao","Chunhua Shen"],"abstract":"Recent progress in semantic segmentation is driven by deep Convolutional\nNeural Networks and large-scale labeled image datasets. However, data labeling\nfor pixel-wise segmentation is tedious and costly. Moreover, a trained model\ncan only make predictions within a set of pre-defined classes. In this paper,\nwe present CANet, a class-agnostic segmentation network that performs few-shot\nsegmentation on new classes with only a few annotated images available. Our\nnetwork consists of a two-branch dense comparison module which performs\nmulti-level feature comparison between the support image and the query image,\nand an iterative optimization module which iteratively refines the predicted\nresults. Furthermore, we introduce an attention mechanism to effectively fuse\ninformation from multiple support examples under the setting of k-shot\nlearning. Experiments on PASCAL VOC 2012 show that our method achieves a mean\nIntersection-over-Union score of 55.4% for 1-shot segmentation and 57.1% for\n5-shot segmentation, outperforming state-of-the-art methods by a large margin\nof 14.6% and 13.2%, respectively.","url_abs":"http://arxiv.org/abs/1903.02351v1","url_pdf":"http://arxiv.org/pdf/1903.02351v1.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":"canet-class-agnostic-segmentation-networks","repo_url":"https://github.com/icoz69/CaNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"few-shot-learning","task_name":"Few-Shot Learning"},{"task_slug":"few-shot-image-segmentation","task_name":"Few-Shot Semantic Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/few-shot-semantic-segmentation-on-pascal-5i-1","task":"Few-Shot Semantic Segmentation","dataset":"PASCAL-5i (1-Shot)","model":"CANet (ResNet-50)","rank_in_archive_order":100,"of":105,"metrics":{"Mean IoU":"55.4"},"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":"CANet (ResNet-50)","rank_in_archive_order":93,"of":96,"metrics":{"Mean IoU":"57.1"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1903.02351","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1903.02351"}},"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/icoz69/CaNet","reach":null}],"summary":{"ran_draft_wrong":1,"ran_honours":1,"unverified":1},"by_repo_kind":{"listed":{"samples":1,"ran":0,"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":3,"samples":[{"code_sha256_prefix":"fac5364e2f53c6db","entry":"conv3x3","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"fac5364e2f53c6db"}},{"code_sha256_prefix":"27504cbeb5811ea6","entry":"outS","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"27504cbeb5811ea6"}},{"code_sha256_prefix":"97b923dc6d571dc0","entry":"Res_Deeplab","repo":"icoz69/CaNet","repo_kind":"listed","path":"one_shot_network.py","file_url":"https://github.com/icoz69/CaNet/blob/HEAD/one_shot_network.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":"97b923dc6d571dc0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}