{"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/learning-distilled-collaboration-graph-for","title":"Learning Distilled Collaboration Graph for Multi-Agent Perception","arxiv_id":"2111.00643","date":"2021-11-01","proceeding":"NeurIPS 2021 12","authors":["Yiming Li","Shunli Ren","Pengxiang Wu","Siheng Chen","Chen Feng","Wenjun Zhang"],"abstract":"To promote better performance-bandwidth trade-off for multi-agent perception, we propose a novel distilled collaboration graph (DiscoGraph) to model trainable, pose-aware, and adaptive collaboration among agents. Our key novelties lie in two aspects. First, we propose a teacher-student framework to train DiscoGraph via knowledge distillation. The teacher model employs an early collaboration with holistic-view inputs; the student model is based on intermediate collaboration with single-view inputs. Our framework trains DiscoGraph by constraining post-collaboration feature maps in the student model to match the correspondences in the teacher model. Second, we propose a matrix-valued edge weight in DiscoGraph. In such a matrix, each element reflects the inter-agent attention at a specific spatial region, allowing an agent to adaptively highlight the informative regions. During inference, we only need to use the student model named as the distilled collaboration network (DiscoNet). Attributed to the teacher-student framework, multiple agents with the shared DiscoNet could collaboratively approach the performance of a hypothetical teacher model with a holistic view. Our approach is validated on V2X-Sim 1.0, a large-scale multi-agent perception dataset that we synthesized using CARLA and SUMO co-simulation. Our quantitative and qualitative experiments in multi-agent 3D object detection show that DiscoNet could not only achieve a better performance-bandwidth trade-off than the state-of-the-art collaborative perception methods, but also bring more straightforward design rationale. Our code is available on https://github.com/ai4ce/DiscoNet.","url_abs":"https://arxiv.org/abs/2111.00643v2","url_pdf":"https://arxiv.org/pdf/2111.00643v2.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":"learning-distilled-collaboration-graph-for","repo_url":"https://github.com/ai4ce/DiscoNet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"learning-distilled-collaboration-graph-for","repo_url":"https://github.com/coperception/coperception","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"3d-object-detection","task_name":"3D Object Detection"},{"task_slug":"knowledge-distillation","task_name":"Knowledge Distillation"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[{"method_slug":"carla","method_name":"CARLA"},{"method_slug":"entropy-regularization","method_name":"Entropy Regularization"},{"method_slug":"ppo","method_name":"PPO"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-object-detection-on-v2x-sim","task":"3D Object Detection","dataset":"V2X-SIM","model":"DiscoNet","rank_in_archive_order":3,"of":5,"metrics":{"mAOE":"0.411","mAP":"22.0","mASE":"0.267","mATE":"0.787"},"uses_additional_data":false},{"leaderboard":"/sota/3d-object-detection-on-v2xset","task":"3D Object Detection","dataset":"V2XSet","model":"DiscoNet","rank_in_archive_order":4,"of":6,"metrics":{"AP0.5 (Noisy)":"0.798","AP0.5 (Perfect)":"0.844","AP0.7 (Noisy)":"0.541","AP0.7 (Perfect)":"0.695"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2111.00643","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2111.00643"}},"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":"deterministic:regex_extraction","url":"https://github.com/ai4ce/DiscoNet","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/coperception/coperception","reach":null}],"summary":{"ran":4,"unverified":2},"by_repo_kind":{"listed":{"samples":6,"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":"2eefc49e3fbd30e1","entry":"ClassificationHead","repo":"coperception/coperception","repo_kind":"listed","path":"coperception/models/det/DiscoNet.py","file_url":"https://github.com/coperception/coperception/blob/HEAD/coperception/models/det/DiscoNet.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":"2eefc49e3fbd30e1"}},{"code_sha256_prefix":"642d741e6a6dde66","entry":"DetModelBase","repo":"coperception/coperception","repo_kind":"listed","path":"coperception/models/det/DiscoNet.py","file_url":"https://github.com/coperception/coperception/blob/HEAD/coperception/models/det/DiscoNet.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":"642d741e6a6dde66"}},{"code_sha256_prefix":"bf62f79dbe83527d","entry":"PixelWeightedFusionSoftmax","repo":"coperception/coperception","repo_kind":"listed","path":"coperception/models/det/DiscoNet.py","file_url":"https://github.com/coperception/coperception/blob/HEAD/coperception/models/det/DiscoNet.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":"bf62f79dbe83527d"}},{"code_sha256_prefix":"9d329a535c4071da","entry":"SingleRegressionHead","repo":"coperception/coperception","repo_kind":"listed","path":"coperception/models/det/DiscoNet.py","file_url":"https://github.com/coperception/coperception/blob/HEAD/coperception/models/det/DiscoNet.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":"9d329a535c4071da"}},{"code_sha256_prefix":"20f1d033168b49c9","entry":"DiscoNet","repo":"coperception/coperception","repo_kind":"listed","path":"coperception/models/det/DiscoNet.py","file_url":"https://github.com/coperception/coperception/blob/HEAD/coperception/models/det/DiscoNet.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":"20f1d033168b49c9"}},{"code_sha256_prefix":"b69c9899c17318e1","entry":"IntermediateModelBase","repo":"coperception/coperception","repo_kind":"listed","path":"coperception/models/det/DiscoNet.py","file_url":"https://github.com/coperception/coperception/blob/HEAD/coperception/models/det/DiscoNet.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":"b69c9899c17318e1"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}