{"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/stronger-vits-with-octic-equivariance","title":"Stronger ViTs With Octic Equivariance","arxiv_id":"2505.15441","date":"2025-05-21","proceeding":null,"authors":["David Nordström","Johan Edstedt","Fredrik Kahl","Georg Bökman"],"abstract":"Recent efforts at scaling computer vision models have established Vision Transformers (ViTs) as the leading architecture. ViTs incorporate weight sharing over image patches as an important inductive bias. In this work, we show that ViTs benefit from incorporating equivariance under the octic group, i.e., reflections and 90-degree rotations, as a further inductive bias. We develop new architectures, octic ViTs, that use octic-equivariant layers and put them to the test on both supervised and self-supervised learning. Through extensive experiments on DeiT-III and DINOv2 training on ImageNet-1K, we show that octic ViTs yield more computationally efficient networks while also improving performance. In particular, we achieve approximately 40% reduction in FLOPs for ViT-H while simultaneously improving both classification and segmentation results.","url_abs":"https://arxiv.org/abs/2505.15441v1","url_pdf":"https://arxiv.org/pdf/2505.15441v1.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":"stronger-vits-with-octic-equivariance","repo_url":"https://github.com/davnords/octic-vits","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":null}],"tasks":[{"task_slug":"inductive-bias","task_name":"Inductive Bias"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2505.15441","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}