{"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/lift-a-surprisingly-simple-lightweight","title":"LiFT: A Surprisingly Simple Lightweight Feature Transform for Dense ViT Descriptors","arxiv_id":"2403.14625","date":"2024-03-21","proceeding":null,"authors":["Saksham Suri","Matthew Walmer","Kamal Gupta","Abhinav Shrivastava"],"abstract":"We present a simple self-supervised method to enhance the performance of ViT features for dense downstream tasks. Our Lightweight Feature Transform (LiFT) is a straightforward and compact postprocessing network that can be applied to enhance the features of any pre-trained ViT backbone. LiFT is fast and easy to train with a self-supervised objective, and it boosts the density of ViT features for minimal extra inference cost. Furthermore, we demonstrate that LiFT can be applied with approaches that use additional task-specific downstream modules, as we integrate LiFT with ViTDet for COCO detection and segmentation. Despite the simplicity of LiFT, we find that it is not simply learning a more complex version of bilinear interpolation. Instead, our LiFT training protocol leads to several desirable emergent properties that benefit ViT features in dense downstream tasks. This includes greater scale invariance for features, and better object boundary maps. By simply training LiFT for a few epochs, we show improved performance on keypoint correspondence, detection, segmentation, and object discovery tasks. Overall, LiFT provides an easy way to unlock the benefits of denser feature arrays for a fraction of the computational cost. For more details, refer to our project page at https://www.cs.umd.edu/~sakshams/LiFT/.","url_abs":"https://arxiv.org/abs/2403.14625v2","url_pdf":"https://arxiv.org/pdf/2403.14625v2.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":"lift-a-surprisingly-simple-lightweight","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"},{"task_slug":"object-discovery","task_name":"Object Discovery"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/feature-upsampling-on-imagenet","task":"Feature Upsampling","dataset":"ImageNet","model":"LiFT","rank_in_archive_order":8,"of":8,"metrics":{"ADCC":"53.0","Average Drop":"66.9","Average Increase":"8.7"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2403.14625","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.14625"}},"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/havrylovv/isegprobe","reach":null}],"summary":{"ran":3},"by_repo_kind":{"listed":{"samples":3,"ran":3,"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":"3aed81779d6fcb10","entry":"DoubleConv","repo":"havrylovv/isegprobe","repo_kind":"listed","path":"core/model/upsamplers/LiFT.py","file_url":"https://github.com/havrylovv/isegprobe/blob/HEAD/core/model/upsamplers/LiFT.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3aed81779d6fcb10"}},{"code_sha256_prefix":"05b8d2312bd1de33","entry":"LiFT","repo":"havrylovv/isegprobe","repo_kind":"listed","path":"core/model/upsamplers/LiFT.py","file_url":"https://github.com/havrylovv/isegprobe/blob/HEAD/core/model/upsamplers/LiFT.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"05b8d2312bd1de33"}},{"code_sha256_prefix":"d6337cc68d29c70f","entry":"Up","repo":"havrylovv/isegprobe","repo_kind":"listed","path":"core/model/upsamplers/LiFT.py","file_url":"https://github.com/havrylovv/isegprobe/blob/HEAD/core/model/upsamplers/LiFT.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d6337cc68d29c70f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}