{"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/dense-gaussian-processes-for-few-shot","title":"Dense Gaussian Processes for Few-Shot Segmentation","arxiv_id":"2110.03674","date":"2021-10-07","proceeding":null,"authors":["Joakim Johnander","Johan Edstedt","Michael Felsberg","Fahad Shahbaz Khan","Martin Danelljan"],"abstract":"Few-shot segmentation is a challenging dense prediction task, which entails segmenting a novel query image given only a small annotated support set. The key problem is thus to design a method that aggregates detailed information from the support set, while being robust to large variations in appearance and context. To this end, we propose a few-shot segmentation method based on dense Gaussian process (GP) regression. Given the support set, our dense GP learns the mapping from local deep image features to mask values, capable of capturing complex appearance distributions. Furthermore, it provides a principled means of capturing uncertainty, which serves as another powerful cue for the final segmentation, obtained by a CNN decoder. Instead of a one-dimensional mask output, we further exploit the end-to-end learning capabilities of our approach to learn a high-dimensional output space for the GP. Our approach sets a new state-of-the-art on the PASCAL-5$^i$ and COCO-20$^i$ benchmarks, achieving an absolute gain of $+8.4$ mIoU in the COCO-20$^i$ 5-shot setting. Furthermore, the segmentation quality of our approach scales gracefully when increasing the support set size, while achieving robust cross-dataset transfer. Code and trained models are available at \\url{https://github.com/joakimjohnander/dgpnet}.","url_abs":"https://arxiv.org/abs/2110.03674v2","url_pdf":"https://arxiv.org/pdf/2110.03674v2.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":"dense-gaussian-processes-for-few-shot","repo_url":"https://github.com/joakimjohnander/dgpnet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"few-shot-image-segmentation","task_name":"Few-Shot Semantic Segmentation"},{"task_slug":"gaussian-processes","task_name":"Gaussian Processes"},{"task_slug":"segmentation","task_name":"Segmentation"}],"methods":[{"method_slug":"gaussian-process","method_name":"Gaussian Process"}],"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":"DGPNet (ResNet-101)","rank_in_archive_order":22,"of":85,"metrics":{"Mean IoU":"46.7"},"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":"DGPNet (ResNet-50)","rank_in_archive_order":35,"of":85,"metrics":{"Mean IoU":"45"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-semantic-segmentation-on-coco-20i-10","task":"Few-Shot Semantic Segmentation","dataset":"COCO-20i (10-shot)","model":"DGPNet (ResNet-101)","rank_in_archive_order":1,"of":4,"metrics":{"Mean IoU":"60.2"},"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":"DGPNet (ResNet-101)","rank_in_archive_order":9,"of":81,"metrics":{"Mean IoU":"57.9"},"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":"DGPNet (ResNet-50)","rank_in_archive_order":14,"of":81,"metrics":{"Mean IoU":"56.2"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-semantic-segmentation-on-coco-20i","task":"Few-Shot Semantic Segmentation","dataset":"COCO-20i -> Pascal VOC (1-shot)","model":"DGPNet (ResNet-101)","rank_in_archive_order":3,"of":13,"metrics":{"Mean IoU":"70.1"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-semantic-segmentation-on-coco-20i","task":"Few-Shot Semantic Segmentation","dataset":"COCO-20i -> Pascal VOC (1-shot)","model":"DGPNet (ResNet-50)","rank_in_archive_order":6,"of":13,"metrics":{"Mean IoU":"68.9"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-semantic-segmentation-on-coco-20i-2","task":"Few-Shot Semantic Segmentation","dataset":"COCO-20i -> Pascal VOC (5-shot)","model":"DGPNet (ResNet-101)","rank_in_archive_order":2,"of":12,"metrics":{"Mean IoU":"78.5"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-semantic-segmentation-on-coco-20i-2","task":"Few-Shot Semantic Segmentation","dataset":"COCO-20i -> Pascal VOC (5-shot)","model":"DGPNet (ResNet-50)","rank_in_archive_order":3,"of":12,"metrics":{"Mean IoU":"77.5"},"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":"DGPNet (ResNet-101)","rank_in_archive_order":53,"of":105,"metrics":{"Mean IoU":"64.8"},"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":"DGPNet (ResNet-50)","rank_in_archive_order":67,"of":105,"metrics":{"Mean IoU":"63.5"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-semantic-segmentation-on-pascal-5i","task":"Few-Shot Semantic Segmentation","dataset":"PASCAL-5i (10-Shot)","model":"DGPNet (ResNet-101)","rank_in_archive_order":1,"of":4,"metrics":{"Mean IoU":"77.7"},"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":"DGPNet (ResNet-101)","rank_in_archive_order":5,"of":96,"metrics":{"Mean IoU":"75.4"},"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":"DGPNet (ResNet-50)","rank_in_archive_order":13,"of":96,"metrics":{"Mean IoU":"73.5"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2110.03674","atlas_url":"https://app.syntology.ai/?focus=2110.03674","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":"2110.03674"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2110.03674\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2110.03674"},"call":"get_concepts_for_paper(arxiv_id=\"2110.03674\")"}],"by_repo":[{"repo":"joakimjohnander/dgpnet","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"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":"b703ec6f57e9d1f3b94997e781dddc9435b3fce0c3b39fc1439655900ebae3e8","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}