{"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-navigation-with-spatial-attention","title":"Visual Navigation with Spatial Attention","arxiv_id":"2104.09807","date":"2021-04-20","proceeding":"CVPR 2021 1","authors":["Bar Mayo","Tamir Hazan","Ayellet Tal"],"abstract":"This work focuses on object goal visual navigation, aiming at finding the location of an object from a given class, where in each step the agent is provided with an egocentric RGB image of the scene. We propose to learn the agent's policy using a reinforcement learning algorithm. Our key contribution is a novel attention probability model for visual navigation tasks. This attention encodes semantic information about observed objects, as well as spatial information about their place. This combination of the \"what\" and the \"where\" allows the agent to navigate toward the sought-after object effectively. The attention model is shown to improve the agent's policy and to achieve state-of-the-art results on commonly-used datasets.","url_abs":"https://arxiv.org/abs/2104.09807v1","url_pdf":"https://arxiv.org/pdf/2104.09807v1.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-navigation-with-spatial-attention","repo_url":"https://github.com/barmayo/spatial_attention","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"navigate","task_name":"Navigate"},{"task_slug":"object","task_name":"Object"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"visual-navigation","task_name":"Visual Navigation"},{"task_slug":"reinforcement-learning-2","task_name":"reinforcement-learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2104.09807","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2104.09807"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/barmayo/spatial_attention","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_draft_wrong":1,"unverified":3},"by_repo_kind":{"listed":{"samples":4,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"f3a3398f34669aea","entry":"normalize_adj","repo":"barmayo/spatial_attention","repo_kind":"listed","path":"models/gcn.py","file_url":"https://github.com/barmayo/spatial_attention/blob/HEAD/models/gcn.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f3a3398f34669aea"}},{"code_sha256_prefix":"4f398ddeb57bc2ba","entry":"gpuify","repo":"barmayo/spatial_attention","repo_kind":"listed","path":"utils/net_util.py","file_url":"https://github.com/barmayo/spatial_attention/blob/HEAD/utils/net_util.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4f398ddeb57bc2ba"}},{"code_sha256_prefix":"63c26f3420b7a699","entry":"resnet_input_transform","repo":"barmayo/spatial_attention","repo_kind":"listed","path":"utils/net_util.py","file_url":"https://github.com/barmayo/spatial_attention/blob/HEAD/utils/net_util.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"63c26f3420b7a699"}},{"code_sha256_prefix":"1fc183e5e42354f9","entry":"toFloatTensor","repo":"barmayo/spatial_attention","repo_kind":"listed","path":"utils/net_util.py","file_url":"https://github.com/barmayo/spatial_attention/blob/HEAD/utils/net_util.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1fc183e5e42354f9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}