{"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/causal-image-modeling-for-efficient-visual","title":"Causal Image Modeling for Efficient Visual Understanding","arxiv_id":"2410.07599","date":"2024-10-10","proceeding":null,"authors":["Feng Wang","Timing Yang","Yaodong Yu","Sucheng Ren","Guoyizhe Wei","Angtian Wang","Wei Shao","Yuyin Zhou","Alan Yuille","Cihang Xie"],"abstract":"In this work, we present a comprehensive analysis of causal image modeling and introduce the Adventurer series models where we treat images as sequences of patch tokens and employ uni-directional language models to learn visual representations. This modeling paradigm allows us to process images in a recurrent formulation with linear complexity relative to the sequence length, which can effectively address the memory and computation explosion issues posed by high-resolution and fine-grained images. In detail, we introduce two simple designs that seamlessly integrate image inputs into the causal inference framework: a global pooling token placed at the beginning of the sequence and a flipping operation between every two layers. Extensive empirical studies demonstrate the significant efficiency and effectiveness of this causal image modeling paradigm. For example, our base-sized Adventurer model attains a competitive test accuracy of 84.0% on the standard ImageNet-1k benchmark with 216 images/s training throughput, which is 5.3 times more efficient than vision transformers to achieve the same result.","url_abs":"https://arxiv.org/abs/2410.07599v1","url_pdf":"https://arxiv.org/pdf/2410.07599v1.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":"causal-image-modeling-for-efficient-visual","repo_url":"https://github.com/wangf3014/Adventurer","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"causal-inference","task_name":"Causal Inference"}],"methods":[{"method_slug":"causal-inference","method_name":"Causal inference"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2410.07599","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}