{"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/speaker-follower-models-for-vision-and","title":"Speaker-Follower Models for Vision-and-Language Navigation","arxiv_id":"1806.02724","date":"2018-06-07","proceeding":"NeurIPS 2018 12","authors":["Daniel Fried","Ronghang Hu","Volkan Cirik","Anna Rohrbach","Jacob Andreas","Louis-Philippe Morency","Taylor Berg-Kirkpatrick","Kate Saenko","Dan Klein","Trevor Darrell"],"abstract":"Navigation guided by natural language instructions presents a challenging\nreasoning problem for instruction followers. Natural language instructions\ntypically identify only a few high-level decisions and landmarks rather than\ncomplete low-level motor behaviors; much of the missing information must be\ninferred based on perceptual context. In machine learning settings, this is\ndoubly challenging: it is difficult to collect enough annotated data to enable\nlearning of this reasoning process from scratch, and also difficult to\nimplement the reasoning process using generic sequence models. Here we describe\nan approach to vision-and-language navigation that addresses both these issues\nwith an embedded speaker model. We use this speaker model to (1) synthesize new\ninstructions for data augmentation and to (2) implement pragmatic reasoning,\nwhich evaluates how well candidate action sequences explain an instruction.\nBoth steps are supported by a panoramic action space that reflects the\ngranularity of human-generated instructions. Experiments show that all three\ncomponents of this approach---speaker-driven data augmentation, pragmatic\nreasoning and panoramic action space---dramatically improve the performance of\na baseline instruction follower, more than doubling the success rate over the\nbest existing approach on a standard benchmark.","url_abs":"http://arxiv.org/abs/1806.02724v2","url_pdf":"http://arxiv.org/pdf/1806.02724v2.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":"speaker-follower-models-for-vision-and","repo_url":"https://github.com/ronghanghu/speaker_follower","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"vision-and-language-navigation","task_name":"Vision and Language Navigation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1806.02724","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1806.02724"}},"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/ronghanghu/speaker_follower","reach":null}],"summary":{"ran_draft_wrong":2},"by_repo_kind":{"listed":{"samples":2,"ran":2,"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":2,"samples":[{"code_sha256_prefix":"ec3e502febcc5d01","entry":"filter_param","repo":"ronghanghu/speaker_follower","repo_kind":"listed","path":"tasks/R2R/train_speaker.py","file_url":"https://github.com/ronghanghu/speaker_follower/blob/HEAD/tasks/R2R/train_speaker.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"ec3e502febcc5d01"}},{"code_sha256_prefix":"4eb280acd405120d","entry":"get_model_prefix","repo":"ronghanghu/speaker_follower","repo_kind":"listed","path":"tasks/R2R/train_speaker.py","file_url":"https://github.com/ronghanghu/speaker_follower/blob/HEAD/tasks/R2R/train_speaker.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"4eb280acd405120d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}