{"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/revisit-recurrent-attention-model-from-an","title":"Revisit Recurrent Attention Model from an Active Sampling Perspective","arxiv_id":null,"date":"2019-09-11","proceeding":"NeurIPS Workshop Neuro_AI 2019 12","authors":["Jialin Lu"],"abstract":"We revisit the Recurrent Attention Model (RAM, Mnih et al. (2014)), a recurrent neural network for visual attention, from an active information sampling perspective. \n\nWe borrow ideas from neuroscience research on the role of active information sampling in the context of visual attention and gaze (Gottlieb, 2018), where the author suggested three types of motives for active information sampling strategies. We find the original RAM model only implements one of them.\n\nWe identify three key weakness of the original RAM and provide a simple solution by adding two extra terms on the objective function. The modified RAM 1) achieves faster convergence, 2) allows dynamic decision making per sample without loss of accuracy, and 3) generalizes much better on longer sequence of glimpses which is not trained for, compared with the original RAM. \n","url_abs":"https://openreview.net/forum?id=HJlVEQt8Lr","url_pdf":"https://openreview.net/pdf?id=HJlVEQt8Lr","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":"revisit-recurrent-attention-model-from-an","repo_url":"https://github.com/luxxxlucy/recurrent-attention-model-revisited","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"decision-making","task_name":"Decision Making"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}