{"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/envedit-environment-editing-for-vision-and","title":"EnvEdit: Environment Editing for Vision-and-Language Navigation","arxiv_id":"2203.15685","date":"2022-03-29","proceeding":"CVPR 2022 1","authors":["Jialu Li","Hao Tan","Mohit Bansal"],"abstract":"In Vision-and-Language Navigation (VLN), an agent needs to navigate through the environment based on natural language instructions. Due to limited available data for agent training and finite diversity in navigation environments, it is challenging for the agent to generalize to new, unseen environments. To address this problem, we propose EnvEdit, a data augmentation method that creates new environments by editing existing environments, which are used to train a more generalizable agent. Our augmented environments can differ from the seen environments in three diverse aspects: style, object appearance, and object classes. Training on these edit-augmented environments prevents the agent from overfitting to existing environments and helps generalize better to new, unseen environments. Empirically, on both the Room-to-Room and the multi-lingual Room-Across-Room datasets, we show that our proposed EnvEdit method gets significant improvements in all metrics on both pre-trained and non-pre-trained VLN agents, and achieves the new state-of-the-art on the test leaderboard. We further ensemble the VLN agents augmented on different edited environments and show that these edit methods are complementary. Code and data are available at https://github.com/jialuli-luka/EnvEdit","url_abs":"https://arxiv.org/abs/2203.15685v1","url_pdf":"https://arxiv.org/pdf/2203.15685v1.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":"envedit-environment-editing-for-vision-and","repo_url":"https://github.com/jialuli-luka/envedit","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"navigate","task_name":"Navigate"},{"task_slug":"vision-and-language-navigation","task_name":"Vision and Language Navigation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/vision-and-language-navigation-on-rxr","task":"Vision and Language Navigation","dataset":"RxR","model":"EnvEdit-PT","rank_in_archive_order":2,"of":6,"metrics":{"ndtw":"64.61"},"uses_additional_data":true}],"syntology":{"syntology_url":"https://syntology.ai/paper/2203.15685","atlas_url":"https://app.syntology.ai/?focus=2203.15685","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.15685"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/jialuli-luka/envedit","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":1,"ran_honours":1,"unverified":3},"by_repo_kind":{"official":{"samples":5,"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":0,"samples":[{"code_sha256_prefix":"0f786c407fb1ee4c","entry":"swish","repo":"jialuli-luka/envedit","repo_kind":"official","path":"hamt_src/models/vilmodel_cmt.py","file_url":"https://github.com/jialuli-luka/envedit/blob/HEAD/hamt_src/models/vilmodel_cmt.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":2,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0f786c407fb1ee4c"}},{"code_sha256_prefix":"fdc64f4c72036ae4","entry":"gelu","repo":"jialuli-luka/envedit","repo_kind":"official","path":"hamt_src/models/vilmodel_cmt.py","file_url":"https://github.com/jialuli-luka/envedit/blob/HEAD/hamt_src/models/vilmodel_cmt.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fdc64f4c72036ae4"}},{"code_sha256_prefix":"7b5b4685db18fbca","entry":"compute_bleu","repo":"jialuli-luka/envedit","repo_kind":"official","path":"r2r_src/bleu.py","file_url":"https://github.com/jialuli-luka/envedit/blob/HEAD/r2r_src/bleu.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7b5b4685db18fbca"}},{"code_sha256_prefix":"e3a90df1a875a38e","entry":"load_nav_graphs","repo":"jialuli-luka/envedit","repo_kind":"official","path":"r2r_src/utils.py","file_url":"https://github.com/jialuli-luka/envedit/blob/HEAD/r2r_src/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e3a90df1a875a38e"}},{"code_sha256_prefix":"6468f9e62900b58c","entry":"read_tsv","repo":"jialuli-luka/envedit","repo_kind":"official","path":"precomute_imagenet_views.py","file_url":"https://github.com/jialuli-luka/envedit/blob/HEAD/precomute_imagenet_views.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6468f9e62900b58c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}