{"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/vision-and-language-navigation-via-causal","title":"Vision-and-Language Navigation via Causal Learning","arxiv_id":"2404.10241","date":"2024-04-16","proceeding":"CVPR 2024 1","authors":["Liuyi Wang","Zongtao He","Ronghao Dang","Mengjiao Shen","Chengju Liu","Qijun Chen"],"abstract":"In the pursuit of robust and generalizable environment perception and language understanding, the ubiquitous challenge of dataset bias continues to plague vision-and-language navigation (VLN) agents, hindering their performance in unseen environments. This paper introduces the generalized cross-modal causal transformer (GOAT), a pioneering solution rooted in the paradigm of causal inference. By delving into both observable and unobservable confounders within vision, language, and history, we propose the back-door and front-door adjustment causal learning (BACL and FACL) modules to promote unbiased learning by comprehensively mitigating potential spurious correlations. Additionally, to capture global confounder features, we propose a cross-modal feature pooling (CFP) module supervised by contrastive learning, which is also shown to be effective in improving cross-modal representations during pre-training. Extensive experiments across multiple VLN datasets (R2R, REVERIE, RxR, and SOON) underscore the superiority of our proposed method over previous state-of-the-art approaches. Code is available at https://github.com/CrystalSixone/VLN-GOAT.","url_abs":"https://arxiv.org/abs/2404.10241v1","url_pdf":"https://arxiv.org/pdf/2404.10241v1.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":"vision-and-language-navigation-via-causal","repo_url":"https://github.com/crystalsixone/vln-goat","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"causal-inference","task_name":"Causal Inference"},{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"vision-and-language-navigation","task_name":"Vision and Language Navigation"},{"task_slug":"visual-navigation","task_name":"Visual Navigation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2404.10241","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.10241"}},"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/crystalsixone/vln-goat","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/CrystalSixone/VLN-GOAT","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":10,"ran_draft_wrong":1,"ran_fixture":1,"unverified":3},"by_repo_kind":{"official":{"samples":15,"ran":12,"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":"c6f7f9ff10d5a6e4","entry":"TransformerEncoder","repo":"CrystalSixone/VLN-GOAT","repo_kind":"official","path":"map_nav_src/models/vilmodel_GOAT.py","file_url":"https://github.com/CrystalSixone/VLN-GOAT/blob/HEAD/map_nav_src/models/vilmodel_GOAT.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c6f7f9ff10d5a6e4"}},{"code_sha256_prefix":"810d160bafcc6c89","entry":"TransformerEncoderLayer","repo":"CrystalSixone/VLN-GOAT","repo_kind":"official","path":"map_nav_src/models/vilmodel_GOAT.py","file_url":"https://github.com/CrystalSixone/VLN-GOAT/blob/HEAD/map_nav_src/models/vilmodel_GOAT.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"810d160bafcc6c89"}},{"code_sha256_prefix":"8f9b89f6d752d797","entry":"create_transformer_encoder","repo":"CrystalSixone/VLN-GOAT","repo_kind":"official","path":"map_nav_src/models/vilmodel_GOAT.py","file_url":"https://github.com/CrystalSixone/VLN-GOAT/blob/HEAD/map_nav_src/models/vilmodel_GOAT.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8f9b89f6d752d797"}},{"code_sha256_prefix":"07969f7041022050","entry":"distributed_init","repo":"crystalsixone/vln-goat","repo_kind":"official","path":"map_nav_src/fairseq/distributed_utils.py","file_url":"https://github.com/crystalsixone/vln-goat/blob/HEAD/map_nav_src/fairseq/distributed_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"07969f7041022050"}},{"code_sha256_prefix":"90b79fe15491de83","entry":"is_master","repo":"crystalsixone/vln-goat","repo_kind":"official","path":"map_nav_src/fairseq/distributed_utils.py","file_url":"https://github.com/crystalsixone/vln-goat/blob/HEAD/map_nav_src/fairseq/distributed_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"90b79fe15491de83"}},{"code_sha256_prefix":"bdab7c5a8cff5650","entry":"load_viewpoint_ids","repo":"crystalsixone/vln-goat","repo_kind":"official","path":"map_nav_src/do_utils/extract_room_type.py","file_url":"https://github.com/crystalsixone/vln-goat/blob/HEAD/map_nav_src/do_utils/extract_room_type.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"bdab7c5a8cff5650"}},{"code_sha256_prefix":"96c2b643194ca603","entry":"pad_tensors_wgrad","repo":"CrystalSixone/VLN-GOAT","repo_kind":"official","path":"map_nav_src/models/vilmodel_GOAT.py","file_url":"https://github.com/CrystalSixone/VLN-GOAT/blob/HEAD/map_nav_src/models/vilmodel_GOAT.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"96c2b643194ca603"}},{"code_sha256_prefix":"f46bad6811c75514","entry":"parse_with_config","repo":"crystalsixone/vln-goat","repo_kind":"official","path":"pretrain_src/parser.py","file_url":"https://github.com/crystalsixone/vln-goat/blob/HEAD/pretrain_src/parser.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f46bad6811c75514"}},{"code_sha256_prefix":"73127ee43d90bbd0","entry":"postprocess_args","repo":"crystalsixone/vln-goat","repo_kind":"official","path":"pretrain_src/parser.py","file_url":"https://github.com/crystalsixone/vln-goat/blob/HEAD/pretrain_src/parser.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"73127ee43d90bbd0"}},{"code_sha256_prefix":"86116165dc99a9a6","entry":"readUnseenScan","repo":"crystalsixone/vln-goat","repo_kind":"official","path":"map_nav_src/do_utils/do_intervention.py","file_url":"https://github.com/crystalsixone/vln-goat/blob/HEAD/map_nav_src/do_utils/do_intervention.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"86116165dc99a9a6"}},{"code_sha256_prefix":"af6f3aa26f7f9738","entry":"read_instr_tsv","repo":"crystalsixone/vln-goat","repo_kind":"official","path":"map_nav_src/do_utils/do_intervention.py","file_url":"https://github.com/crystalsixone/vln-goat/blob/HEAD/map_nav_src/do_utils/do_intervention.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"af6f3aa26f7f9738"}},{"code_sha256_prefix":"82bdf940665aeeb4","entry":"safe_readline","repo":"crystalsixone/vln-goat","repo_kind":"official","path":"map_nav_src/fairseq/binarizer.py","file_url":"https://github.com/crystalsixone/vln-goat/blob/HEAD/map_nav_src/fairseq/binarizer.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"82bdf940665aeeb4"}},{"code_sha256_prefix":"f446dce9e2e63b44","entry":"CausalImageEmbeddings","repo":"CrystalSixone/VLN-GOAT","repo_kind":"official","path":"map_nav_src/models/vilmodel_GOAT.py","file_url":"https://github.com/CrystalSixone/VLN-GOAT/blob/HEAD/map_nav_src/models/vilmodel_GOAT.py","link_basis":"first_harvest_node","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":"f446dce9e2e63b44"}},{"code_sha256_prefix":"199e96db5edd0edd","entry":"all_reduce","repo":"crystalsixone/vln-goat","repo_kind":"official","path":"map_nav_src/fairseq/distributed_utils.py","file_url":"https://github.com/crystalsixone/vln-goat/blob/HEAD/map_nav_src/fairseq/distributed_utils.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":"199e96db5edd0edd"}},{"code_sha256_prefix":"a22399a1ec12c22c","entry":"build_feature_extractor","repo":"crystalsixone/vln-goat","repo_kind":"official","path":"map_nav_src/do_utils/extract_room_type.py","file_url":"https://github.com/crystalsixone/vln-goat/blob/HEAD/map_nav_src/do_utils/extract_room_type.py","link_basis":"first_harvest_node","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":"a22399a1ec12c22c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}