{"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/loftup-learning-a-coordinate-based-feature","title":"LoftUp: Learning a Coordinate-Based Feature Upsampler for Vision Foundation Models","arxiv_id":"2504.14032","date":"2025-04-18","proceeding":null,"authors":["Haiwen Huang","Anpei Chen","Volodymyr Havrylov","Andreas Geiger","Dan Zhang"],"abstract":"Vision foundation models (VFMs) such as DINOv2 and CLIP have achieved impressive results on various downstream tasks, but their limited feature resolution hampers performance in applications requiring pixel-level understanding. Feature upsampling offers a promising direction to address this challenge. In this work, we identify two critical factors for enhancing feature upsampling: the upsampler architecture and the training objective. For the upsampler architecture, we introduce a coordinate-based cross-attention transformer that integrates the high-resolution images with coordinates and low-resolution VFM features to generate sharp, high-quality features. For the training objective, we propose constructing high-resolution pseudo-groundtruth features by leveraging class-agnostic masks and self-distillation. Our approach effectively captures fine-grained details and adapts flexibly to various input and feature resolutions. Through experiments, we demonstrate that our approach significantly outperforms existing feature upsampling techniques across various downstream tasks. Our code is released at https://github.com/andrehuang/loftup.","url_abs":"https://arxiv.org/abs/2504.14032v1","url_pdf":"https://arxiv.org/pdf/2504.14032v1.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":"loftup-learning-a-coordinate-based-feature","repo_url":"https://github.com/andrehuang/loftup","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"loftup-learning-a-coordinate-based-feature","repo_url":"https://github.com/havrylovv/isegprobe","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"feature-upsampling","task_name":"Feature Upsampling"}],"methods":[{"method_slug":"clip","method_name":"CLIP"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2504.14032","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.14032"}},"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/andrehuang/loftup","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/havrylovv/isegprobe","reach":null}],"summary":{"ran_violates":2,"unverified":4},"by_repo_kind":{"official":{"samples":6,"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":0,"samples":[{"code_sha256_prefix":"f912c209e9c899ca","entry":"divisible_by","repo":"andrehuang/loftup","repo_kind":"official","path":"ema.py","file_url":"https://github.com/andrehuang/loftup/blob/HEAD/ema.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f912c209e9c899ca"}},{"code_sha256_prefix":"aa5486a3650902d8","entry":"exists","repo":"andrehuang/loftup","repo_kind":"official","path":"ema.py","file_url":"https://github.com/andrehuang/loftup/blob/HEAD/ema.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"aa5486a3650902d8"}},{"code_sha256_prefix":"6d0d864b192e60ac","entry":"apply_jitter","repo":"andrehuang/loftup","repo_kind":"official","path":"training_utils.py","file_url":"https://github.com/andrehuang/loftup/blob/HEAD/training_utils.py","link_basis":"harvester_set","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":"6d0d864b192e60ac"}},{"code_sha256_prefix":"405aa5d9f24e4bb4","entry":"entropy","repo":"andrehuang/loftup","repo_kind":"official","path":"training_utils.py","file_url":"https://github.com/andrehuang/loftup/blob/HEAD/training_utils.py","link_basis":"harvester_set","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":"405aa5d9f24e4bb4"}},{"code_sha256_prefix":"18a4926263a1a4af","entry":"get_module_device","repo":"andrehuang/loftup","repo_kind":"official","path":"ema.py","file_url":"https://github.com/andrehuang/loftup/blob/HEAD/ema.py","link_basis":"harvester_set","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":"18a4926263a1a4af"}},{"code_sha256_prefix":"8669462a8a711826","entry":"sample_transform","repo":"andrehuang/loftup","repo_kind":"official","path":"training_utils.py","file_url":"https://github.com/andrehuang/loftup/blob/HEAD/training_utils.py","link_basis":"harvester_set","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":"8669462a8a711826"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}