{"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/visual-pre-training-for-navigation-what-can","title":"Visual Pre-training for Navigation: What Can We Learn from Noise?","arxiv_id":"2207.00052","date":"2022-06-30","proceeding":null,"authors":["Yanwei Wang","Ching-Yun Ko","Pulkit Agrawal"],"abstract":"One powerful paradigm in visual navigation is to predict actions from observations directly. Training such an end-to-end system allows representations useful for downstream tasks to emerge automatically. However, the lack of inductive bias makes this system data inefficient. We hypothesize a sufficient representation of the current view and the goal view for a navigation policy can be learned by predicting the location and size of a crop of the current view that corresponds to the goal. We further show that training such random crop prediction in a self-supervised fashion purely on synthetic noise images transfers well to natural home images. The learned representation can then be bootstrapped to learn a navigation policy efficiently with little interaction data. The code is available at https://yanweiw.github.io/noise2ptz","url_abs":"https://arxiv.org/abs/2207.00052v3","url_pdf":"https://arxiv.org/pdf/2207.00052v3.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":"visual-pre-training-for-navigation-what-can","repo_url":"https://github.com/yanweiw/noise2ptz","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"inductive-bias","task_name":"Inductive Bias"},{"task_slug":"navigate","task_name":"Navigate"},{"task_slug":"visual-navigation","task_name":"Visual Navigation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2207.00052","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}