{"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/domain-adaptive-2d-human-pose-estimation-via","title":"Domain-Adaptive 2D Human Pose Estimation via Dual Teachers in Extremely Low-Light Conditions","arxiv_id":"2407.15451","date":"2024-07-22","proceeding":null,"authors":["Yihao Ai","Yifei Qi","Bo wang","Yu Cheng","Xinchao Wang","Robby T. Tan"],"abstract":"Existing 2D human pose estimation research predominantly concentrates on well-lit scenarios, with limited exploration of poor lighting conditions, which are a prevalent aspect of daily life. Recent studies on low-light pose estimation require the use of paired well-lit and low-light images with ground truths for training, which are impractical due to the inherent challenges associated with annotation on low-light images. To this end, we introduce a novel approach that eliminates the need for low-light ground truths. Our primary novelty lies in leveraging two complementary-teacher networks to generate more reliable pseudo labels, enabling our model achieves competitive performance on extremely low-light images without the need for training with low-light ground truths. Our framework consists of two stages. In the first stage, our model is trained on well-lit data with low-light augmentations. In the second stage, we propose a dual-teacher framework to utilize the unlabeled low-light data, where a center-based main teacher produces the pseudo labels for relatively visible cases, while a keypoints-based complementary teacher focuses on producing the pseudo labels for the missed persons of the main teacher. With the pseudo labels from both teachers, we propose a person-specific low-light augmentation to challenge a student model in training to outperform the teachers. Experimental results on real low-light dataset (ExLPose-OCN) show, our method achieves 6.8% (2.4 AP) improvement over the state-of-the-art (SOTA) method, despite no low-light ground-truth data is used in our approach, in contrast to the SOTA method. Our code will be available at:https://github.com/ayh015-dev/DA-LLPose.","url_abs":"https://arxiv.org/abs/2407.15451v2","url_pdf":"https://arxiv.org/pdf/2407.15451v2.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":"domain-adaptive-2d-human-pose-estimation-via","repo_url":"https://github.com/ayh015-dev/da-llpose","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"2d-human-pose-estimation","task_name":"2D Human Pose Estimation"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/2d-human-pose-estimation-on-exlpose-ll-e","task":"2D Human Pose Estimation","dataset":"ExLPose-LL-E","model":"DA-LLPose","rank_in_archive_order":1,"of":1,"metrics":{"AP":"5.0"},"uses_additional_data":false},{"leaderboard":"/sota/2d-human-pose-estimation-on-exlpose-ll-h","task":"2D Human Pose Estimation","dataset":"ExLPose-LL-H","model":"DA-LLPose","rank_in_archive_order":1,"of":1,"metrics":{"AP":"18.6"},"uses_additional_data":false},{"leaderboard":"/sota/2d-human-pose-estimation-on-exlpose-ll-n","task":"2D Human Pose Estimation","dataset":"ExLPose-LL-N","model":"DA-LLPose","rank_in_archive_order":1,"of":1,"metrics":{"AP":"35.6"},"uses_additional_data":false},{"leaderboard":"/sota/2d-human-pose-estimation-on-exlpose-ocn-a7m3","task":"2D Human Pose Estimation","dataset":"ExLPose-OCN-A7M3","model":"DA-LLPose","rank_in_archive_order":1,"of":1,"metrics":{"AP":"39.1"},"uses_additional_data":false},{"leaderboard":"/sota/2d-human-pose-estimation-on-exlpose-ocn","task":"2D Human Pose Estimation","dataset":"ExLPose-OCN-RICOH3","model":"DA-LLPose","rank_in_archive_order":1,"of":1,"metrics":{"AP":"36.2"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2407.15451","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.15451"}},"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/ayh015-dev/da-llpose","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":2,"ran_fixture":6,"ran_honours":1,"ran":2,"unverified":2},"by_repo_kind":{"official":{"samples":13,"ran":11,"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":13,"samples":[{"code_sha256_prefix":"2d04867e070c9f3b","entry":"absorb_heat","repo":"ayh015-dev/da-llpose","repo_kind":"official","path":"lib/core/match.py","file_url":"https://github.com/ayh015-dev/da-llpose/blob/HEAD/lib/core/match.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2d04867e070c9f3b"}},{"code_sha256_prefix":"68194dcec6efb51a","entry":"cal_area_2_torch","repo":"ayh015-dev/da-llpose","repo_kind":"official","path":"lib/core/nms.py","file_url":"https://github.com/ayh015-dev/da-llpose/blob/HEAD/lib/core/nms.py","link_basis":"plan_row","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"68194dcec6efb51a"}},{"code_sha256_prefix":"45aee6b94ac4a933","entry":"fit_gaussian_heatmap","repo":"ayh015-dev/da-llpose","repo_kind":"official","path":"lib/core/match.py","file_url":"https://github.com/ayh015-dev/da-llpose/blob/HEAD/lib/core/match.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"45aee6b94ac4a933"}},{"code_sha256_prefix":"fb92a64737e6147a","entry":"get_heat_value","repo":"ayh015-dev/da-llpose","repo_kind":"official","path":"lib/core/nms.py","file_url":"https://github.com/ayh015-dev/da-llpose/blob/HEAD/lib/core/nms.py","link_basis":"plan_row","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"fb92a64737e6147a"}},{"code_sha256_prefix":"dc9000f59685be5e","entry":"get_locations","repo":"ayh015-dev/da-llpose","repo_kind":"official","path":"lib/core/inference.py","file_url":"https://github.com/ayh015-dev/da-llpose/blob/HEAD/lib/core/inference.py","link_basis":"plan_row","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"dc9000f59685be5e"}},{"code_sha256_prefix":"432f8f0b9ec09d8f","entry":"get_reg_poses","repo":"ayh015-dev/da-llpose","repo_kind":"official","path":"lib/core/inference.py","file_url":"https://github.com/ayh015-dev/da-llpose/blob/HEAD/lib/core/inference.py","link_basis":"plan_row","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"432f8f0b9ec09d8f"}},{"code_sha256_prefix":"cdea90667046c71c","entry":"make_input","repo":"ayh015-dev/da-llpose","repo_kind":"official","path":"lib/core/loss_comp.py","file_url":"https://github.com/ayh015-dev/da-llpose/blob/HEAD/lib/core/loss_comp.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"cdea90667046c71c"}},{"code_sha256_prefix":"2745bc38a4aa584a","entry":"make_test_dataloader","repo":"ayh015-dev/da-llpose","repo_kind":"official","path":"lib/dataset/build.py","file_url":"https://github.com/ayh015-dev/da-llpose/blob/HEAD/lib/dataset/build.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2745bc38a4aa584a"}},{"code_sha256_prefix":"bb9ed3e4607e2be5","entry":"nms_core","repo":"ayh015-dev/da-llpose","repo_kind":"official","path":"lib/core/nms.py","file_url":"https://github.com/ayh015-dev/da-llpose/blob/HEAD/lib/core/nms.py","link_basis":"plan_row","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"bb9ed3e4607e2be5"}},{"code_sha256_prefix":"c39aba611d5b56d8","entry":"offset_to_pose","repo":"ayh015-dev/da-llpose","repo_kind":"official","path":"lib/core/inference.py","file_url":"https://github.com/ayh015-dev/da-llpose/blob/HEAD/lib/core/inference.py","link_basis":"plan_row","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c39aba611d5b56d8"}},{"code_sha256_prefix":"c7cbca3e6472edd4","entry":"unnormalized_gaussian2d","repo":"ayh015-dev/da-llpose","repo_kind":"official","path":"lib/core/match.py","file_url":"https://github.com/ayh015-dev/da-llpose/blob/HEAD/lib/core/match.py","link_basis":"plan_row","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c7cbca3e6472edd4"}},{"code_sha256_prefix":"983e45bff55979f5","entry":"build_dataset","repo":"ayh015-dev/da-llpose","repo_kind":"official","path":"lib/dataset/build.py","file_url":"https://github.com/ayh015-dev/da-llpose/blob/HEAD/lib/dataset/build.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"983e45bff55979f5"}},{"code_sha256_prefix":"bbb37470905b1d7c","entry":"make_dataloader","repo":"ayh015-dev/da-llpose","repo_kind":"official","path":"lib/dataset/build.py","file_url":"https://github.com/ayh015-dev/da-llpose/blob/HEAD/lib/dataset/build.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"bbb37470905b1d7c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}