{"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/dip-unsupervised-dense-in-context-post","title":"DIP: Unsupervised Dense In-Context Post-training of Visual Representations","arxiv_id":"2506.18463","date":"2025-06-23","proceeding":null,"authors":["Sophia Sirko-Galouchenko","Spyros Gidaris","Antonin Vobecky","Andrei Bursuc","Nicolas Thome"],"abstract":"We introduce DIP, a novel unsupervised post-training method designed to enhance dense image representations in large-scale pretrained vision encoders for in-context scene understanding. Unlike prior approaches that rely on complex self-distillation architectures, our method trains the vision encoder using pseudo-tasks that explicitly simulate downstream in-context scenarios, inspired by meta-learning principles. To enable post-training on unlabeled data, we propose an automatic mechanism for generating in-context tasks that combines a pretrained diffusion model and the vision encoder itself. DIP is simple, unsupervised, and computationally efficient, requiring less than 9 hours on a single A100 GPU. By learning dense representations through pseudo in-context tasks, it achieves strong performance across a wide variety of downstream real-world in-context scene understanding tasks. It outperforms both the initial vision encoder and prior methods, offering a practical and effective solution for improving dense representations. Code available here: https://github.com/sirkosophia/DIP","url_abs":"https://arxiv.org/abs/2506.18463v1","url_pdf":"https://arxiv.org/pdf/2506.18463v1.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":"dip-unsupervised-dense-in-context-post","repo_url":"https://github.com/sirkosophia/dip","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":null,"task_name":"GPU"},{"task_slug":"meta-learning","task_name":"Meta-Learning"},{"task_slug":"scene-understanding","task_name":"Scene Understanding"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2506.18463","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.18463"}},"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/sirkosophia/dip","reach":null}],"summary":{"ran":1,"unverified":3},"by_repo_kind":{"official":{"samples":4,"ran":1,"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":4,"samples":[{"code_sha256_prefix":"d8c583f1cc12d333","entry":"Mlp","repo":"sirkosophia/dip","repo_kind":"official","path":"models/dipnet.py","file_url":"https://github.com/sirkosophia/dip/blob/HEAD/models/dipnet.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":"d8c583f1cc12d333"}},{"code_sha256_prefix":"f89c343321e531d5","entry":"DIPNet","repo":"sirkosophia/dip","repo_kind":"official","path":"models/dipnet.py","file_url":"https://github.com/sirkosophia/dip/blob/HEAD/models/dipnet.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":"f89c343321e531d5"}},{"code_sha256_prefix":"d3a365231452f8e0","entry":"DinoVitFeatureExtractorFinetune","repo":"sirkosophia/dip","repo_kind":"official","path":"models/dipnet.py","file_url":"https://github.com/sirkosophia/dip/blob/HEAD/models/dipnet.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":"d3a365231452f8e0"}},{"code_sha256_prefix":"c646bad8910d971e","entry":"set_requires_grad","repo":"sirkosophia/dip","repo_kind":"official","path":"models/dipnet.py","file_url":"https://github.com/sirkosophia/dip/blob/HEAD/models/dipnet.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":"c646bad8910d971e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}