{"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/self-supervised-learning-from-images-with-a","title":"Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture","arxiv_id":"2301.08243","date":"2023-01-19","proceeding":"CVPR 2023 1","authors":["Mahmoud Assran","Quentin Duval","Ishan Misra","Piotr Bojanowski","Pascal Vincent","Michael Rabbat","Yann Lecun","Nicolas Ballas"],"abstract":"This paper demonstrates an approach for learning highly semantic image representations without relying on hand-crafted data-augmentations. We introduce the Image-based Joint-Embedding Predictive Architecture (I-JEPA), a non-generative approach for self-supervised learning from images. The idea behind I-JEPA is simple: from a single context block, predict the representations of various target blocks in the same image. A core design choice to guide I-JEPA towards producing semantic representations is the masking strategy; specifically, it is crucial to (a) sample target blocks with sufficiently large scale (semantic), and to (b) use a sufficiently informative (spatially distributed) context block. Empirically, when combined with Vision Transformers, we find I-JEPA to be highly scalable. For instance, we train a ViT-Huge/14 on ImageNet using 16 A100 GPUs in under 72 hours to achieve strong downstream performance across a wide range of tasks, from linear classification to object counting and depth prediction.","url_abs":"https://arxiv.org/abs/2301.08243v3","url_pdf":"https://arxiv.org/pdf/2301.08243v3.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":"self-supervised-learning-from-images-with-a","repo_url":"https://github.com/facebookresearch/ijepa","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"self-supervised-learning-from-images-with-a","repo_url":"https://github.com/gaasher/I-JEPA","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"self-supervised-learning-from-images-with-a","repo_url":"https://github.com/vectorinstitute/mmlearn","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"self-supervised-learning-from-images-with-a","repo_url":"https://github.com/waterdisappear/sar-jepa","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"self-supervised-learning-from-images-with-a","repo_url":"https://github.com/waterdisappear/sar-kpga","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"self-supervised-learning-from-images-with-a","repo_url":"https://github.com/lightly-ai/lightly","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"self-supervised-learning-from-images-with-a","repo_url":"https://gitlab.com/birder/birder","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"depth-estimation","task_name":"Depth Estimation"},{"task_slug":"depth-prediction","task_name":"Depth Prediction"},{"task_slug":"object-counting","task_name":"Object Counting"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2301.08243","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.08243"}},"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/lightly-ai/lightly","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/waterdisappear/sar-kpga","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://gitlab.com/birder/birder","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/vectorinstitute/mmlearn","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/gaasher/I-JEPA","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/waterdisappear/sar-jepa","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/facebookresearch/ijepa","reach":null}],"summary":{"ran":2,"ran_honours":1,"ran_draft_wrong":2,"unverified":9},"by_repo_kind":{"official":{"samples":3,"ran":2,"repositories":1},"listed":{"samples":11,"ran":3,"repositories":2}},"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":13,"samples":[{"code_sha256_prefix":"5a10f46fdda5375c","entry":"Block","repo":"facebookresearch/ijepa","repo_kind":"official","path":"src/models/vision_transformer.py","file_url":"https://github.com/facebookresearch/ijepa/blob/HEAD/src/models/vision_transformer.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"5a10f46fdda5375c"}},{"code_sha256_prefix":"abc90f0c6dffd99f","entry":"GF","repo":"waterdisappear/sar-jepa","repo_kind":"listed","path":"Pretraining/models_lomar.py","file_url":"https://github.com/waterdisappear/sar-jepa/blob/HEAD/Pretraining/models_lomar.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":"abc90f0c6dffd99f"}},{"code_sha256_prefix":"fc939725b0bb127b","entry":"get_2d_sincos_pos_embed","repo":"facebookresearch/ijepa","repo_kind":"official","path":"src/models/vision_transformer.py","file_url":"https://github.com/facebookresearch/ijepa/blob/HEAD/src/models/vision_transformer.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"fc939725b0bb127b"}},{"code_sha256_prefix":"ab8156d726620d7e","entry":"get_rpe_config","repo":"waterdisappear/sar-jepa","repo_kind":"listed","path":"Pretraining/models_lomar.py","file_url":"https://github.com/waterdisappear/sar-jepa/blob/HEAD/Pretraining/models_lomar.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"ab8156d726620d7e"}},{"code_sha256_prefix":"b67bfbf8a86f8ae3","entry":"get_single_rpe_config","repo":"waterdisappear/sar-jepa","repo_kind":"listed","path":"Pretraining/models_lomar.py","file_url":"https://github.com/waterdisappear/sar-jepa/blob/HEAD/Pretraining/models_lomar.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"b67bfbf8a86f8ae3"}},{"code_sha256_prefix":"d5d4d27df91c3a11","entry":"Attention","repo":"waterdisappear/sar-jepa","repo_kind":"listed","path":"Pretraining/models_lomar.py","file_url":"https://github.com/waterdisappear/sar-jepa/blob/HEAD/Pretraining/models_lomar.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":"d5d4d27df91c3a11"}},{"code_sha256_prefix":"6710d315e3285047","entry":"Block","repo":"waterdisappear/sar-jepa","repo_kind":"listed","path":"Pretraining/models_lomar.py","file_url":"https://github.com/waterdisappear/sar-jepa/blob/HEAD/Pretraining/models_lomar.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":"6710d315e3285047"}},{"code_sha256_prefix":"534c33c21ec7b299","entry":"IJEPAPredictor","repo":"lightly-ai/lightly","repo_kind":"listed","path":"lightly/models/modules/ijepa.py","file_url":"https://github.com/lightly-ai/lightly/blob/HEAD/lightly/models/modules/ijepa.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":"534c33c21ec7b299"}},{"code_sha256_prefix":"91e43c1af69c43ab","entry":"MaskedAutoencoderViT","repo":"waterdisappear/sar-jepa","repo_kind":"listed","path":"Pretraining/models_lomar.py","file_url":"https://github.com/waterdisappear/sar-jepa/blob/HEAD/Pretraining/models_lomar.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":"91e43c1af69c43ab"}},{"code_sha256_prefix":"9d96610a96ece7b7","entry":"VisionTransformerPredictor","repo":"facebookresearch/ijepa","repo_kind":"official","path":"src/models/vision_transformer.py","file_url":"https://github.com/facebookresearch/ijepa/blob/HEAD/src/models/vision_transformer.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":"9d96610a96ece7b7"}},{"code_sha256_prefix":"7f5fc306914d0a48","entry":"build_rpe","repo":"waterdisappear/sar-jepa","repo_kind":"listed","path":"Pretraining/models_lomar.py","file_url":"https://github.com/waterdisappear/sar-jepa/blob/HEAD/Pretraining/models_lomar.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":"7f5fc306914d0a48"}},{"code_sha256_prefix":"d5148a7973cd80a8","entry":"get_bucket_ids_2d","repo":"waterdisappear/sar-jepa","repo_kind":"listed","path":"Pretraining/models_lomar.py","file_url":"https://github.com/waterdisappear/sar-jepa/blob/HEAD/Pretraining/models_lomar.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":"d5148a7973cd80a8"}},{"code_sha256_prefix":"0a8854a10b0caba2","entry":"iRPE","repo":"waterdisappear/sar-jepa","repo_kind":"listed","path":"Pretraining/models_lomar.py","file_url":"https://github.com/waterdisappear/sar-jepa/blob/HEAD/Pretraining/models_lomar.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":"0a8854a10b0caba2"}},{"code_sha256_prefix":"6ea577bc7d8c4a62","entry":"iRPE_Cross","repo":"waterdisappear/sar-jepa","repo_kind":"listed","path":"Pretraining/models_lomar.py","file_url":"https://github.com/waterdisappear/sar-jepa/blob/HEAD/Pretraining/models_lomar.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":"6ea577bc7d8c4a62"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}