{"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/efficient-image-pre-training-with-siamese","title":"Efficient Image Pre-Training with Siamese Cropped Masked Autoencoders","arxiv_id":"2403.17823","date":"2024-03-26","proceeding":null,"authors":["Alexandre Eymaël","Renaud Vandeghen","Anthony Cioppa","Silvio Giancola","Bernard Ghanem","Marc Van Droogenbroeck"],"abstract":"Self-supervised pre-training of image encoders is omnipresent in the literature, particularly following the introduction of Masked autoencoders (MAE). Current efforts attempt to learn object-centric representations from motion in videos. In particular, SiamMAE recently introduced a Siamese network, training a shared-weight encoder from two frames of a video with a high asymmetric masking ratio (95%). In this work, we propose CropMAE, an alternative approach to the Siamese pre-training introduced by SiamMAE. Our method specifically differs by exclusively considering pairs of cropped images sourced from the same image but cropped differently, deviating from the conventional pairs of frames extracted from a video. CropMAE therefore alleviates the need for video datasets, while maintaining competitive performances and drastically reducing pre-training and learning time. Furthermore, we demonstrate that CropMAE learns similar object-centric representations without explicit motion, showing that current self-supervised learning methods do not learn such representations from explicit object motion, but rather thanks to the implicit image transformations that occur between the two views. Finally, CropMAE achieves the highest masking ratio to date (98.5%), enabling the reconstruction of images using only two visible patches. Our code is available at https://github.com/alexandre-eymael/CropMAE.","url_abs":"https://arxiv.org/abs/2403.17823v2","url_pdf":"https://arxiv.org/pdf/2403.17823v2.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":"efficient-image-pre-training-with-siamese","repo_url":"https://github.com/alexandre-eymael/cropmae","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"object","task_name":"Object"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2403.17823","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.17823"}},"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/alexandre-eymael/cropmae","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/alexandreeymael/CropMAE","reach":{"status":"gone","observed_at":"2026-09-17","how":"tree_404+repo_404"}}],"summary":{"ran":3,"unverified":4},"by_repo_kind":{"official":{"samples":7,"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":"fd90af86a74696fc","entry":"create_blank_image","repo":"alexandre-eymael/cropmae","repo_kind":"official","path":"misc/util.py","file_url":"https://github.com/alexandre-eymael/cropmae/blob/HEAD/misc/util.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":"fd90af86a74696fc"}},{"code_sha256_prefix":"ec8de49a4b0b9deb","entry":"evaluate_on_davis","repo":"alexandre-eymael/cropmae","repo_kind":"official","path":"downstreams/propagation/start.py","file_url":"https://github.com/alexandre-eymael/cropmae/blob/HEAD/downstreams/propagation/start.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":"ec8de49a4b0b9deb"}},{"code_sha256_prefix":"5ab50bab8a11be05","entry":"run_one_image_mae","repo":"alexandre-eymael/cropmae","repo_kind":"official","path":"misc/util.py","file_url":"https://github.com/alexandre-eymael/cropmae/blob/HEAD/misc/util.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":"5ab50bab8a11be05"}},{"code_sha256_prefix":"3a14f8ea402d70f1","entry":"evaluate_on_jhmdb","repo":"alexandre-eymael/cropmae","repo_kind":"official","path":"downstreams/propagation/start.py","file_url":"https://github.com/alexandre-eymael/cropmae/blob/HEAD/downstreams/propagation/start.py","link_basis":"first_harvest_node","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":"3a14f8ea402d70f1"}},{"code_sha256_prefix":"1feb343d9d220faa","entry":"evaluate_on_vip","repo":"alexandre-eymael/cropmae","repo_kind":"official","path":"downstreams/propagation/start.py","file_url":"https://github.com/alexandre-eymael/cropmae/blob/HEAD/downstreams/propagation/start.py","link_basis":"first_harvest_node","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":"1feb343d9d220faa"}},{"code_sha256_prefix":"718a42749c76f61d","entry":"main","repo":"alexandre-eymael/cropmae","repo_kind":"official","path":"downstreams/propagation/davis_evaluation/evaluation_method.py","file_url":"https://github.com/alexandre-eymael/cropmae/blob/HEAD/downstreams/propagation/davis_evaluation/evaluation_method.py","link_basis":"first_harvest_node","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":"718a42749c76f61d"}},{"code_sha256_prefix":"ce9e09b03e8c96de","entry":"parse_img","repo":"alexandre-eymael/cropmae","repo_kind":"official","path":"misc/util.py","file_url":"https://github.com/alexandre-eymael/cropmae/blob/HEAD/misc/util.py","link_basis":"first_harvest_node","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":"ce9e09b03e8c96de"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}