{"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/a-refreshed-similarity-based-upsampler-for","title":"A Refreshed Similarity-based Upsampler for Direct High-Ratio Feature Upsampling","arxiv_id":"2407.02283","date":"2024-07-02","proceeding":null,"authors":["Minghao Zhou","Hong Wang","Yefeng Zheng","Deyu Meng"],"abstract":"Feature upsampling is a fundamental and indispensable ingredient of almost all current network structures for image segmentation tasks. Recently, a popular similarity-based feature upsampling pipeline has been proposed, which utilizes a high-resolution feature as guidance to help upsample the low-resolution deep feature based on their local similarity. Albeit achieving promising performance, this pipeline has specific limitations: 1) HR query and LR key features are not well aligned; 2) the similarity between query-key features is computed based on the fixed inner product form; 3) neighbor selection is coarsely operated on LR features, resulting in mosaic artifacts. These shortcomings make the existing methods along this pipeline primarily applicable to hierarchical network architectures with iterative features as guidance and they are not readily extended to a broader range of structures, especially for a direct high-ratio upsampling. Against the issues, we meticulously optimize every methodological design. Specifically, we firstly propose an explicitly controllable query-key feature alignment from both semantic-aware and detail-aware perspectives, and then construct a parameterized paired central difference convolution block for flexibly calculating the similarity between the well-aligned query-key features. Besides, we develop a fine-grained neighbor selection strategy on HR features, which is simple yet effective for alleviating mosaic artifacts. Based on these careful designs, we systematically construct a refreshed similarity-based feature upsampling framework named ReSFU. Extensive experiments substantiate that our proposed ReSFU is finely applicable to various types of architectures in a direct high-ratio upsampling manner, and consistently achieves satisfactory performance on different segmentation applications, showing superior generality and ease of deployment.","url_abs":"https://arxiv.org/abs/2407.02283v1","url_pdf":"https://arxiv.org/pdf/2407.02283v1.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":"a-refreshed-similarity-based-upsampler-for","repo_url":"https://github.com/zmhhmz/resfu","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"feature-upsampling","task_name":"Feature Upsampling"},{"task_slug":"image-segmentation","task_name":"Image Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/feature-upsampling-on-imagenet","task":"Feature Upsampling","dataset":"ImageNet","model":"ReSFU","rank_in_archive_order":6,"of":8,"metrics":{"ADCC":"59.4","Average Drop":"14.5","Average Increase":"24.0"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2407.02283","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.02283"}},"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/zmhhmz/resfu","reach":{"status":"ok"}}],"summary":{"ran":6,"unverified":2},"by_repo_kind":{"official":{"samples":8,"ran":6,"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":8,"samples":[{"code_sha256_prefix":"a669df2cd07c07bb","entry":"calculate_file_sha256","repo":"zmhhmz/resfu","repo_kind":"official","path":"mmsegmentation/.dev_scripts/gather_models.py","file_url":"https://github.com/zmhhmz/resfu/blob/HEAD/mmsegmentation/.dev_scripts/gather_models.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a669df2cd07c07bb"}},{"code_sha256_prefix":"b4af221dcd087500","entry":"create_gaussian_kernel","repo":"zmhhmz/resfu","repo_kind":"official","path":"demo/resfu.py","file_url":"https://github.com/zmhhmz/resfu/blob/HEAD/demo/resfu.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b4af221dcd087500"}},{"code_sha256_prefix":"b8bb3de40cf61c64","entry":"dump_yaml_and_check_difference","repo":"zmhhmz/resfu","repo_kind":"official","path":"mmsegmentation/.dev_scripts/update_model_index.py","file_url":"https://github.com/zmhhmz/resfu/blob/HEAD/mmsegmentation/.dev_scripts/update_model_index.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b8bb3de40cf61c64"}},{"code_sha256_prefix":"b9e0b82131912b70","entry":"get_collection_name_list","repo":"zmhhmz/resfu","repo_kind":"official","path":"mmsegmentation/.dev_scripts/update_model_index.py","file_url":"https://github.com/zmhhmz/resfu/blob/HEAD/mmsegmentation/.dev_scripts/update_model_index.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b9e0b82131912b70"}},{"code_sha256_prefix":"88d68650d669bb11","entry":"get_final_iter","repo":"zmhhmz/resfu","repo_kind":"official","path":"mmsegmentation/.dev_scripts/gather_models.py","file_url":"https://github.com/zmhhmz/resfu/blob/HEAD/mmsegmentation/.dev_scripts/gather_models.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"88d68650d669bb11"}},{"code_sha256_prefix":"4037fd6bcb9ca210","entry":"process_checkpoint","repo":"zmhhmz/resfu","repo_kind":"official","path":"mmsegmentation/.dev_scripts/gather_models.py","file_url":"https://github.com/zmhhmz/resfu/blob/HEAD/mmsegmentation/.dev_scripts/gather_models.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4037fd6bcb9ca210"}},{"code_sha256_prefix":"dbbc38f85ae9361f","entry":"check_url","repo":"zmhhmz/resfu","repo_kind":"official","path":"mmsegmentation/.dev_scripts/check_urls.py","file_url":"https://github.com/zmhhmz/resfu/blob/HEAD/mmsegmentation/.dev_scripts/check_urls.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":"dbbc38f85ae9361f"}},{"code_sha256_prefix":"75819240e9ae42d0","entry":"get_model_info","repo":"zmhhmz/resfu","repo_kind":"official","path":"mmsegmentation/.dev_scripts/update_model_index.py","file_url":"https://github.com/zmhhmz/resfu/blob/HEAD/mmsegmentation/.dev_scripts/update_model_index.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":"75819240e9ae42d0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}