{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/silc-improving-vision-language-pretraining","title":"SILC: Improving Vision Language Pretraining with Self-Distillation","arxiv_id":"2310.13355","date":"2023-10-20","proceeding":null,"authors":["Muhammad Ferjad Naeem","Yongqin Xian","Xiaohua Zhai","Lukas Hoyer","Luc van Gool","Federico Tombari"],"abstract":"Image-Text pretraining on web-scale image caption datasets has become the default recipe for open vocabulary classification and retrieval models thanks to the success of CLIP and its variants. Several works have also used CLIP features for dense prediction tasks and have shown the emergence of open-set abilities. However, the contrastive objective used by these models only focuses on image-text alignment and does not incentivise image feature learning for dense prediction tasks. In this work, we introduce SILC, a novel framework for vision language pretraining. SILC improves image-text contrastive learning with the simple addition of local-to-global correspondence learning by self-distillation. We show that distilling local image features from an exponential moving average (EMA) teacher model significantly improves model performance on dense predictions tasks like detection and segmentation, while also providing improvements on image-level tasks such as classification and retrieval. SILC models sets a new state of the art for zero-shot classification, few shot classification, image and text retrieval, zero-shot segmentation, and open vocabulary segmentation. We further show that SILC features greatly benefit open vocabulary detection, captioning and visual question answering.","url_abs":"https://arxiv.org/abs/2310.13355v2","url_pdf":"https://arxiv.org/pdf/2310.13355v2.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":[],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"open-vocabulary-semantic-segmentation","task_name":"Open Vocabulary Semantic Segmentation"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"retrieval","task_name":"Retrieval"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"text-retrieval","task_name":"Text Retrieval"},{"task_slug":"visual-question-answering-1","task_name":"Visual Question Answering"},{"task_slug":"zero-shot-segmentation","task_name":"Zero Shot Segmentation"},{"task_slug":"zero-shot-learning","task_name":"Zero-Shot Learning"},{"task_slug":null,"task_name":"zero-shot-classification"}],"methods":[{"method_slug":"clip","method_name":"CLIP"},{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/open-vocabulary-semantic-segmentation-on-2","task":"Open Vocabulary Semantic Segmentation","dataset":"ADE20K-150","model":"SILC","rank_in_archive_order":5,"of":23,"metrics":{"mIoU":"37.7"},"uses_additional_data":false},{"leaderboard":"/sota/open-vocabulary-semantic-segmentation-on-3","task":"Open Vocabulary Semantic Segmentation","dataset":"ADE20K-847","model":"SILC","rank_in_archive_order":7,"of":19,"metrics":{"mIoU":"15.0"},"uses_additional_data":false},{"leaderboard":"/sota/open-vocabulary-semantic-segmentation-on-7","task":"Open Vocabulary Semantic Segmentation","dataset":"PASCAL Context-459","model":"SILC","rank_in_archive_order":1,"of":15,"metrics":{"mIoU":"25.8"},"uses_additional_data":false},{"leaderboard":"/sota/open-vocabulary-semantic-segmentation-on-1","task":"Open Vocabulary Semantic Segmentation","dataset":"PASCAL Context-59","model":"SILC","rank_in_archive_order":2,"of":24,"metrics":{"mIoU":"63.5"},"uses_additional_data":false},{"leaderboard":"/sota/open-vocabulary-semantic-segmentation-on-5","task":"Open Vocabulary Semantic Segmentation","dataset":"PascalVOC-20","model":"SILC","rank_in_archive_order":2,"of":20,"metrics":{"mIoU":"97.6"},"uses_additional_data":false},{"leaderboard":"/sota/open-vocabulary-semantic-segmentation-on-9","task":"Open Vocabulary Semantic Segmentation","dataset":"PascalVOC-20b","model":"SILC","rank_in_archive_order":3,"of":4,"metrics":{"mIoU":"82.5"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2310.13355","atlas_url":"https://app.syntology.ai/?focus=2310.13355","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2310.13355"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2310.13355\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2310.13355"},"call":"get_concepts_for_paper(arxiv_id=\"2310.13355\")"}],"by_repo":[],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":"the archive holds no code link for this paper","arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"34c41cf14329a87c421c3a8be94296205c99859c53c3b95c2980ccac5d3245bf","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}