{"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/inter-region-affinity-distillation-for-road","title":"Inter-Region Affinity Distillation for Road Marking Segmentation","arxiv_id":"2004.05304","date":"2020-04-11","proceeding":"CVPR 2020 6","authors":["Yuenan Hou","Zheng Ma","Chunxiao Liu","Tak-Wai Hui","Chen Change Loy"],"abstract":"We study the problem of distilling knowledge from a large deep teacher network to a much smaller student network for the task of road marking segmentation. In this work, we explore a novel knowledge distillation (KD) approach that can transfer 'knowledge' on scene structure more effectively from a teacher to a student model. Our method is known as Inter-Region Affinity KD (IntRA-KD). It decomposes a given road scene image into different regions and represents each region as a node in a graph. An inter-region affinity graph is then formed by establishing pairwise relationships between nodes based on their similarity in feature distribution. To learn structural knowledge from the teacher network, the student is required to match the graph generated by the teacher. The proposed method shows promising results on three large-scale road marking segmentation benchmarks, i.e., ApolloScape, CULane and LLAMAS, by taking various lightweight models as students and ResNet-101 as the teacher. IntRA-KD consistently brings higher performance gains on all lightweight models, compared to previous distillation methods. Our code is available at https://github.com/cardwing/Codes-for-IntRA-KD.","url_abs":"https://arxiv.org/abs/2004.05304v1","url_pdf":"https://arxiv.org/pdf/2004.05304v1.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":"inter-region-affinity-distillation-for-road","repo_url":"https://github.com/cardwing/Codes-for-IntRA-KD","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"knowledge-distillation","task_name":"Knowledge Distillation"},{"task_slug":"lane-detection","task_name":"Lane Detection"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[{"method_slug":"knowledge-distillation","method_name":"Knowledge Distillation"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/lane-detection-on-culane","task":"Lane Detection","dataset":"CULane","model":"ERFNet-IntRA-KD (ours)","rank_in_archive_order":55,"of":63,"metrics":{"F1 score":"72.4"},"uses_additional_data":false},{"leaderboard":"/sota/semantic-segmentation-on-apolloscape","task":"Semantic Segmentation","dataset":"ApolloScape","model":"ERFNet-IntRA-KD (ours)","rank_in_archive_order":1,"of":2,"metrics":{"mIoU":"43.2"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2004.05304","atlas_url":"https://app.syntology.ai/?focus=2004.05304","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.05304"}},"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/cardwing/Codes-for-IntRA-KD","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":4},"by_repo_kind":{"official":{"samples":4,"ran":4,"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":"83877d60072f32f1","entry":"conv3x3","repo":"cardwing/Codes-for-IntRA-KD","repo_kind":"official","path":"models/fc_resnet.py","file_url":"https://github.com/cardwing/Codes-for-IntRA-KD/blob/HEAD/models/fc_resnet.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"83877d60072f32f1"}},{"code_sha256_prefix":"e39a36da1de1c9d7","entry":"fc_resnet101","repo":"cardwing/Codes-for-IntRA-KD","repo_kind":"official","path":"models/fc_sense_resnet.py","file_url":"https://github.com/cardwing/Codes-for-IntRA-KD/blob/HEAD/models/fc_sense_resnet.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e39a36da1de1c9d7"}},{"code_sha256_prefix":"b3e1baa4a4f5eb5e","entry":"fc_resnet18","repo":"cardwing/Codes-for-IntRA-KD","repo_kind":"official","path":"models/fc_resnet.py","file_url":"https://github.com/cardwing/Codes-for-IntRA-KD/blob/HEAD/models/fc_resnet.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b3e1baa4a4f5eb5e"}},{"code_sha256_prefix":"bcaec687dfb304f4","entry":"fc_resnet34","repo":"cardwing/Codes-for-IntRA-KD","repo_kind":"official","path":"models/fc_resnet.py","file_url":"https://github.com/cardwing/Codes-for-IntRA-KD/blob/HEAD/models/fc_resnet.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bcaec687dfb304f4"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}