{"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/singular-value-fine-tuning-few-shot-1","title":"Singular Value Fine-tuning: Few-shot Segmentation requires Few-parameters Fine-tuning","arxiv_id":"2206.06122","date":"2022-06-13","proceeding":null,"authors":["Yanpeng Sun","Qiang Chen","Xiangyu He","Jian Wang","Haocheng Feng","Junyu Han","Errui Ding","Jian Cheng","Zechao Li","Jingdong Wang"],"abstract":"Freezing the pre-trained backbone has become a standard paradigm to avoid overfitting in few-shot segmentation. In this paper, we rethink the paradigm and explore a new regime: {\\em fine-tuning a small part of parameters in the backbone}. We present a solution to overcome the overfitting problem, leading to better model generalization on learning novel classes. Our method decomposes backbone parameters into three successive matrices via the Singular Value Decomposition (SVD), then {\\em only fine-tunes the singular values} and keeps others frozen. The above design allows the model to adjust feature representations on novel classes while maintaining semantic clues within the pre-trained backbone. We evaluate our {\\em Singular Value Fine-tuning (SVF)} approach on various few-shot segmentation methods with different backbones. We achieve state-of-the-art results on both Pascal-5$^i$ and COCO-20$^i$ across 1-shot and 5-shot settings. Hopefully, this simple baseline will encourage researchers to rethink the role of backbone fine-tuning in few-shot settings. The source code and models will be available at \\url{https://github.com/syp2ysy/SVF}.","url_abs":"https://arxiv.org/abs/2206.06122v2","url_pdf":"https://arxiv.org/pdf/2206.06122v2.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":"singular-value-fine-tuning-few-shot-1","repo_url":"https://github.com/syp2ysy/SVF","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"paddle","reach":null}],"tasks":[{"task_slug":"few-shot-image-segmentation","task_name":"Few-Shot Semantic Segmentation"}],"methods":[],"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":"BAM (SVF, ResNet-50)","rank_in_archive_order":15,"of":85,"metrics":{"Mean IoU":"48.47"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-semantic-segmentation-on-coco-20i-1","task":"Few-Shot Semantic Segmentation","dataset":"COCO-20i (1-shot)","model":"PFENet (SVF, ResNet-50)","rank_in_archive_order":17,"of":85,"metrics":{"Mean IoU":"48.02"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-semantic-segmentation-on-coco-20i-1","task":"Few-Shot Semantic Segmentation","dataset":"COCO-20i (1-shot)","model":"BAM (SVF, VGG-16)","rank_in_archive_order":39,"of":85,"metrics":{"Mean IoU":"43.76"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-semantic-segmentation-on-coco-20i-1","task":"Few-Shot Semantic Segmentation","dataset":"COCO-20i (1-shot)","model":"PFENet (SVF, VGG-16)","rank_in_archive_order":51,"of":85,"metrics":{"Mean IoU":"42.24"},"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":"PFENet (SVF, ResNet-50)","rank_in_archive_order":20,"of":81,"metrics":{"Mean IoU":"54.38"},"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":"BAM (SVF, ResNet-50)","rank_in_archive_order":22,"of":81,"metrics":{"Mean IoU":"53.87"},"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":"PFENet (SVF, VGG-16)","rank_in_archive_order":42,"of":81,"metrics":{"Mean IoU":"49.49"},"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":"BAM (SVF, VGG-16)","rank_in_archive_order":45,"of":81,"metrics":{"Mean IoU":"49.07"},"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":"BAM (SVF, ResNet-50)","rank_in_archive_order":15,"of":105,"metrics":{"FB-IoU":"80.13","Mean IoU":"68.95"},"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":"PFENet (SVF, ResNet-50)","rank_in_archive_order":20,"of":105,"metrics":{"FB-IoU":"79.07","Mean IoU":"68.15"},"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":"BAM (SVF, VGG-16)","rank_in_archive_order":52,"of":105,"metrics":{"Mean IoU":"64.87"},"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":"PFENet (SVF, VGG-16)","rank_in_archive_order":58,"of":105,"metrics":{"Mean IoU":"64.33"},"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":"BAM (SVF, ResNet-50)","rank_in_archive_order":18,"of":96,"metrics":{"FB-IoU":"83.17","Mean IoU":"72.28"},"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":"PFENet (SVF, ResNet-50)","rank_in_archive_order":21,"of":96,"metrics":{"FB-IoU":"82.77","Mean IoU":"71.82"},"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":"PFENet (SVF, VGG-16)","rank_in_archive_order":44,"of":96,"metrics":{"Mean IoU":"69.8"},"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":"BAM (SVF, VGG-16)","rank_in_archive_order":52,"of":96,"metrics":{"Mean IoU":"69.11"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2206.06122","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.06122"}},"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":"deterministic:regex_extraction","url":"https://github.com/syp2ysy/SVF","reach":null}],"summary":{"ran_draft_wrong":1,"ran_honours":1,"unverified":2},"by_repo_kind":{"official":{"samples":1,"ran":1,"repositories":1},"community":{"samples":3,"ran":1,"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":"46c465264fc07006","entry":"d_nsvd","repo":"zechao-li/SVF-pytorch","repo_kind":"community","path":"svf.py","file_url":"https://github.com/zechao-li/SVF-pytorch/blob/HEAD/svf.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"46c465264fc07006"}},{"code_sha256_prefix":"abd97f26f98fa5b0","entry":"round_to_nearest","repo":"syp2ysy/SVF","repo_kind":"official","path":"svf.py","file_url":"https://github.com/syp2ysy/SVF/blob/HEAD/svf.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"abd97f26f98fa5b0"}},{"code_sha256_prefix":"e839efa71c7b59e3","entry":"replace_fullrank_with_lowrank","repo":"zechao-li/SVF-pytorch","repo_kind":"community","path":"svf.py","file_url":"https://github.com/zechao-li/SVF-pytorch/blob/HEAD/svf.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":"e839efa71c7b59e3"}},{"code_sha256_prefix":"72b4beced0f39b70","entry":"round_to_nearest","repo":"zechao-li/SVF-pytorch","repo_kind":"community","path":"svf.py","file_url":"https://github.com/zechao-li/SVF-pytorch/blob/HEAD/svf.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"72b4beced0f39b70"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}