{"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/correlational-image-modeling-for-self","title":"Correlational Image Modeling for Self-Supervised Visual Pre-Training","arxiv_id":"2303.12670","date":"2023-03-22","proceeding":"CVPR 2023 1","authors":["Wei Li","Jiahao Xie","Chen Change Loy"],"abstract":"We introduce Correlational Image Modeling (CIM), a novel and surprisingly effective approach to self-supervised visual pre-training. Our CIM performs a simple pretext task: we randomly crop image regions (exemplars) from an input image (context) and predict correlation maps between the exemplars and the context. Three key designs enable correlational image modeling as a nontrivial and meaningful self-supervisory task. First, to generate useful exemplar-context pairs, we consider cropping image regions with various scales, shapes, rotations, and transformations. Second, we employ a bootstrap learning framework that involves online and target encoders. During pre-training, the former takes exemplars as inputs while the latter converts the context. Third, we model the output correlation maps via a simple cross-attention block, within which the context serves as queries and the exemplars offer values and keys. We show that CIM performs on par or better than the current state of the art on self-supervised and transfer benchmarks.","url_abs":"https://arxiv.org/abs/2303.12670v3","url_pdf":"https://arxiv.org/pdf/2303.12670v3.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":"correlational-image-modeling-for-self","repo_url":"https://github.com/weivision/correlational-image-modeling","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2303.12670","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2303.12670"}},"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/weivision/correlational-image-modeling","reach":null}],"summary":{"ran":6,"unverified":1},"by_repo_kind":{"official":{"samples":7,"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":7,"samples":[{"code_sha256_prefix":"e2796dfadcc960a6","entry":"Attention","repo":"weivision/correlational-image-modeling","repo_kind":"official","path":"models/cim.py","file_url":"https://github.com/weivision/correlational-image-modeling/blob/HEAD/models/cim.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"e2796dfadcc960a6"}},{"code_sha256_prefix":"c7a6f7abc4b8ea31","entry":"Block","repo":"weivision/correlational-image-modeling","repo_kind":"official","path":"models/cim.py","file_url":"https://github.com/weivision/correlational-image-modeling/blob/HEAD/models/cim.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"c7a6f7abc4b8ea31"}},{"code_sha256_prefix":"54f35c7a30196f16","entry":"CorrelationBlockV1","repo":"weivision/correlational-image-modeling","repo_kind":"official","path":"models/cim.py","file_url":"https://github.com/weivision/correlational-image-modeling/blob/HEAD/models/cim.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"54f35c7a30196f16"}},{"code_sha256_prefix":"2e7d0ca574d0d946","entry":"CrossAttention","repo":"weivision/correlational-image-modeling","repo_kind":"official","path":"models/cim.py","file_url":"https://github.com/weivision/correlational-image-modeling/blob/HEAD/models/cim.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"2e7d0ca574d0d946"}},{"code_sha256_prefix":"5757bb967031e292","entry":"CrossBlock","repo":"weivision/correlational-image-modeling","repo_kind":"official","path":"models/cim.py","file_url":"https://github.com/weivision/correlational-image-modeling/blob/HEAD/models/cim.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"5757bb967031e292"}},{"code_sha256_prefix":"b5adec75df0db70f","entry":"PatchEmbed","repo":"weivision/correlational-image-modeling","repo_kind":"official","path":"models/cim.py","file_url":"https://github.com/weivision/correlational-image-modeling/blob/HEAD/models/cim.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"b5adec75df0db70f"}},{"code_sha256_prefix":"4834c5522760f95c","entry":"CorrelationalAutoencoderViT","repo":"weivision/correlational-image-modeling","repo_kind":"official","path":"models/cim.py","file_url":"https://github.com/weivision/correlational-image-modeling/blob/HEAD/models/cim.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"4834c5522760f95c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}