{"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/doubly-deformable-aggregation-of-covariance","title":"Doubly Deformable Aggregation of Covariance Matrices for Few-shot Segmentation","arxiv_id":"2208.00306","date":"2022-07-30","proceeding":null,"authors":["Zhitong Xiong","Haopeng Li","Xiao Xiang Zhu"],"abstract":"Training semantic segmentation models with few annotated samples has great potential in various real-world applications. For the few-shot segmentation task, the main challenge is how to accurately measure the semantic correspondence between the support and query samples with limited training data. To address this problem, we propose to aggregate the learnable covariance matrices with a deformable 4D Transformer to effectively predict the segmentation map. Specifically, in this work, we first devise a novel hard example mining mechanism to learn covariance kernels for the Gaussian process. The learned covariance kernel functions have great advantages over existing cosine similarity-based methods in correspondence measurement. Based on the learned covariance kernels, an efficient doubly deformable 4D Transformer module is designed to adaptively aggregate feature similarity maps into segmentation results. By combining these two designs, the proposed method can not only set new state-of-the-art performance on public benchmarks, but also converge extremely faster than existing methods. Experiments on three public datasets have demonstrated the effectiveness of our method.","url_abs":"https://arxiv.org/abs/2208.00306v1","url_pdf":"https://arxiv.org/pdf/2208.00306v1.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":"doubly-deformable-aggregation-of-covariance","repo_url":"https://github.com/shadowxzt/dacm-few-shot.pytorch","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"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"},{"task_slug":"semantic-correspondence","task_name":"Semantic correspondence"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"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":"DACM (VAT, ResNet-50)","rank_in_archive_order":46,"of":85,"metrics":{"FB-IoU":"69.4","Mean IoU":"43"},"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":"DACM (ResNet-50)","rank_in_archive_order":61,"of":85,"metrics":{"FB-IoU":"68.9","Mean IoU":"40.6"},"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":"DACM (VAT, ResNet-50)","rank_in_archive_order":44,"of":81,"metrics":{"FB-IoU":"72.9","Mean IoU":"49.2"},"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":"DACM (ResNet-50)","rank_in_archive_order":49,"of":81,"metrics":{"FB-IoU":"71.6","Mean IoU":"48.1"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-semantic-segmentation-on-fss-1000-1","task":"Few-Shot Semantic Segmentation","dataset":"FSS-1000 (1-shot)","model":"DACM (ResNet-101)","rank_in_archive_order":1,"of":24,"metrics":{"Mean IoU":"90.8"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-semantic-segmentation-on-fss-1000-1","task":"Few-Shot Semantic Segmentation","dataset":"FSS-1000 (1-shot)","model":"DACM (ResNet-50)","rank_in_archive_order":2,"of":24,"metrics":{"Mean IoU":"90.7"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-semantic-segmentation-on-fss-1000-5","task":"Few-Shot Semantic Segmentation","dataset":"FSS-1000 (5-shot)","model":"DACM (ResNet-101)","rank_in_archive_order":1,"of":22,"metrics":{"Mean IoU":"91.7"},"uses_additional_data":false},{"leaderboard":"/sota/few-shot-semantic-segmentation-on-fss-1000-5","task":"Few-Shot Semantic Segmentation","dataset":"FSS-1000 (5-shot)","model":"DACM (ResNet-50)","rank_in_archive_order":2,"of":22,"metrics":{"Mean IoU":"91.6"},"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":"DACM (VAT, ResNet-101)","rank_in_archive_order":14,"of":105,"metrics":{"FB-IoU":"79.4","Mean IoU":"69.1"},"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":"DACM (ResNet-101)","rank_in_archive_order":25,"of":105,"metrics":{"FB-IoU":"78.9","Mean IoU":"67.5"},"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":"DACM (VAT, ResNet-50)","rank_in_archive_order":33,"of":105,"metrics":{"FB-IoU":"78.6","Mean IoU":"66.8"},"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":"DACM (ResNet-50)","rank_in_archive_order":46,"of":105,"metrics":{"FB-IoU":"77.8","Mean IoU":"65.7"},"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":"DACM (VGG-16)","rank_in_archive_order":73,"of":105,"metrics":{"FB-IoU":"75.5","Mean IoU":"61.8"},"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":"DACM (VAT, ResNet-101)","rank_in_archive_order":14,"of":96,"metrics":{"FB-IoU":"83.1","Mean IoU":"73.3"},"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":"DACM (VAT, ResNet-50)","rank_in_archive_order":23,"of":96,"metrics":{"FB-IoU":"81.7","Mean IoU":"71.7"},"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":"DACM (ResNet-101)","rank_in_archive_order":27,"of":96,"metrics":{"FB-IoU":"81.5","Mean IoU":"71.4"},"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":"DACM (ResNet-50)","rank_in_archive_order":33,"of":96,"metrics":{"FB-IoU":"81.3","Mean IoU":"70.9"},"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":"DACM (VGG-16)","rank_in_archive_order":72,"of":96,"metrics":{"FB-IoU":"77.8","Mean IoU":"65.7"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2208.00306","atlas_url":"https://app.syntology.ai/?focus=2208.00306","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2208.00306"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/shadowxzt/dacm-few-shot.pytorch","reach":null}],"summary":{"ran":2},"by_repo_kind":{"official":{"samples":2,"ran":2,"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":2,"samples":[{"code_sha256_prefix":"adcd53d99f2ea63d","entry":"DAttentionModule","repo":"shadowxzt/dacm-few-shot.pytorch","repo_kind":"official","path":"model/base/multimodal_df.py","file_url":"https://github.com/shadowxzt/dacm-few-shot.pytorch/blob/HEAD/model/base/multimodal_df.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"adcd53d99f2ea63d"}},{"code_sha256_prefix":"97a403009efc85d8","entry":"LayerNormProxy","repo":"shadowxzt/dacm-few-shot.pytorch","repo_kind":"official","path":"model/base/multimodal_df.py","file_url":"https://github.com/shadowxzt/dacm-few-shot.pytorch/blob/HEAD/model/base/multimodal_df.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"97a403009efc85d8"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}