{"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/perceive-ground-reason-and-act-a-benchmark","title":"Perceive, Ground, Reason, and Act: A Benchmark for General-purpose Visual Representation","arxiv_id":"2211.15402","date":"2022-11-28","proceeding":null,"authors":["Jiangyong Huang","William Yicheng Zhu","Baoxiong Jia","Zan Wang","Xiaojian Ma","Qing Li","Siyuan Huang"],"abstract":"Current computer vision models, unlike the human visual system, cannot yet achieve general-purpose visual understanding. Existing efforts to create a general vision model are limited in the scope of assessed tasks and offer no overarching framework to perform them holistically. We present a new comprehensive benchmark, General-purpose Visual Understanding Evaluation (G-VUE), covering the full spectrum of visual cognitive abilities with four functional domains $\\unicode{x2014}$ Perceive, Ground, Reason, and Act. The four domains are embodied in 11 carefully curated tasks, from 3D reconstruction to visual reasoning and manipulation. Along with the benchmark, we provide a general encoder-decoder framework to allow for the evaluation of arbitrary visual representation on all 11 tasks. We evaluate various pre-trained visual representations with our framework and observe that (1) Transformer-based visual backbone generally outperforms CNN-based backbone on G-VUE, (2) visual representations from vision-language pre-training are superior to those with vision-only pre-training across visual tasks. With G-VUE, we provide a holistic evaluation standard to motivate research toward building general-purpose visual systems via obtaining more general-purpose visual representations.","url_abs":"https://arxiv.org/abs/2211.15402v1","url_pdf":"https://arxiv.org/pdf/2211.15402v1.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":"perceive-ground-reason-and-act-a-benchmark","repo_url":"https://github.com/wllmzhu/G-VUE","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok"}}],"tasks":[{"task_slug":"3d-reconstruction","task_name":"3D Reconstruction"},{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"visual-reasoning","task_name":"Visual Reasoning"}],"methods":[],"datasets_introduced":[{"slug":"g-vue","name":"G-VUE","full_name":"General-purpose Visual Understanding Evaluation"}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2211.15402","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}