{"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/learning-to-rank-patches-for-unbiased-image","title":"Learning to Rank Patches for Unbiased Image Redundancy Reduction","arxiv_id":"2404.00680","date":"2024-03-31","proceeding":"CVPR 2024 1","authors":["Yang Luo","Zhineng Chen","Peng Zhou","Zuxuan Wu","Xieping Gao","Yu-Gang Jiang"],"abstract":"Images suffer from heavy spatial redundancy because pixels in neighboring regions are spatially correlated. Existing approaches strive to overcome this limitation by reducing less meaningful image regions. However, current leading methods rely on supervisory signals. They may compel models to preserve content that aligns with labeled categories and discard content belonging to unlabeled categories. This categorical inductive bias makes these methods less effective in real-world scenarios. To address this issue, we propose a self-supervised framework for image redundancy reduction called Learning to Rank Patches (LTRP). We observe that image reconstruction of masked image modeling models is sensitive to the removal of visible patches when the masking ratio is high (e.g., 90\\%). Building upon it, we implement LTRP via two steps: inferring the semantic density score of each patch by quantifying variation between reconstructions with and without this patch, and learning to rank the patches with the pseudo score. The entire process is self-supervised, thus getting out of the dilemma of categorical inductive bias. We design extensive experiments on different datasets and tasks. The results demonstrate that LTRP outperforms both supervised and other self-supervised methods due to the fair assessment of image content.","url_abs":"https://arxiv.org/abs/2404.00680v2","url_pdf":"https://arxiv.org/pdf/2404.00680v2.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":"learning-to-rank-patches-for-unbiased-image","repo_url":"https://github.com/irslu/ltrp","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"image-reconstruction","task_name":"Image Reconstruction"},{"task_slug":"inductive-bias","task_name":"Inductive Bias"},{"task_slug":"learning-to-rank","task_name":"Learning-To-Rank"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2404.00680","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.00680"}},"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/irslu/ltrp","reach":{"status":"ok"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/irsLu/ltrp","reach":{"status":"ok"}}],"summary":{"ran":5},"by_repo_kind":{"official":{"samples":5,"ran":5,"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":5,"samples":[{"code_sha256_prefix":"78df363571c80e0a","entry":"LearnToRankPatchMIM","repo":"irsLu/ltrp","repo_kind":"official","path":"models_ltrp.py","file_url":"https://github.com/irsLu/ltrp/blob/HEAD/models_ltrp.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":"78df363571c80e0a"}},{"code_sha256_prefix":"c820d379d7d8bfcb","entry":"cluster_dpc_knn","repo":"irslu/ltrp","repo_kind":"official","path":"score_net/ltrp_cluster.py","file_url":"https://github.com/irslu/ltrp/blob/HEAD/score_net/ltrp_cluster.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":"c820d379d7d8bfcb"}},{"code_sha256_prefix":"1e125c8d8e5f4f15","entry":"index_points","repo":"irslu/ltrp","repo_kind":"official","path":"score_net/ltrp_cluster.py","file_url":"https://github.com/irslu/ltrp/blob/HEAD/score_net/ltrp_cluster.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":"1e125c8d8e5f4f15"}},{"code_sha256_prefix":"067e18aafaabbacf","entry":"jsd","repo":"irslu/ltrp","repo_kind":"official","path":"utils/ltrp_loss.py","file_url":"https://github.com/irslu/ltrp/blob/HEAD/utils/ltrp_loss.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"067e18aafaabbacf"}},{"code_sha256_prefix":"0c60f989099fa93a","entry":"kld","repo":"irslu/ltrp","repo_kind":"official","path":"utils/ltrp_loss.py","file_url":"https://github.com/irslu/ltrp/blob/HEAD/utils/ltrp_loss.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0c60f989099fa93a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}