{"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/less-is-more-removing-text-regions-improves","title":"Less is More: Removing Text-regions Improves CLIP Training Efficiency and Robustness","arxiv_id":"2305.05095","date":"2023-05-08","proceeding":null,"authors":["Liangliang Cao","BoWen Zhang","Chen Chen","Yinfei Yang","Xianzhi Du","Wencong Zhang","Zhiyun Lu","Yantao Zheng"],"abstract":"The CLIP (Contrastive Language-Image Pre-training) model and its variants are becoming the de facto backbone in many applications. However, training a CLIP model from hundreds of millions of image-text pairs can be prohibitively expensive. Furthermore, the conventional CLIP model doesn't differentiate between the visual semantics and meaning of text regions embedded in images. This can lead to non-robustness when the text in the embedded region doesn't match the image's visual appearance. In this paper, we discuss two effective approaches to improve the efficiency and robustness of CLIP training: (1) augmenting the training dataset while maintaining the same number of optimization steps, and (2) filtering out samples that contain text regions in the image. By doing so, we significantly improve the classification and retrieval accuracy on public benchmarks like ImageNet and CoCo. Filtering out images with text regions also protects the model from typographic attacks. To verify this, we build a new dataset named ImageNet with Adversarial Text Regions (ImageNet-Attr). Our filter-based CLIP model demonstrates a top-1 accuracy of 68.78\\%, outperforming previous models whose accuracy was all below 50\\%.","url_abs":"https://arxiv.org/abs/2305.05095v1","url_pdf":"https://arxiv.org/pdf/2305.05095v1.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":"less-is-more-removing-text-regions-improves","repo_url":"https://github.com/apple/axlearn/blob/main/axlearn/vision/imagenet_adversarial_text/","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"jax","reach":null}],"tasks":[{"task_slug":"adversarial-text","task_name":"Adversarial Text"},{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[{"method_slug":"clip","method_name":"CLIP"}],"datasets_introduced":[{"slug":"imagenet-atr","name":"ImageNet-Atr","full_name":"ImageNet with Adversarial Text Regions"}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2305.05095","atlas_url":"https://app.syntology.ai/?focus=2305.05095","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":"2305.05095"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2305.05095\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2305.05095"},"call":"get_concepts_for_paper(arxiv_id=\"2305.05095\")"}],"by_repo":[{"repo":"apple/axlearn","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2407.18961"],"harvested_for_calls":[{"arxiv_id":"2407.18961","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2407.18961"},"call":"get_harvested_code_for_paper(arxiv_id=\"2407.18961\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","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":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"96439e3943e96cc7dc06b16830bcc25a9b89d5e1527a393106875a9f1767a981","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}