{"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/where2comm-communication-efficient","title":"Where2comm: Communication-Efficient Collaborative Perception via Spatial Confidence Maps","arxiv_id":"2209.12836","date":"2022-09-26","proceeding":null,"authors":["Yue Hu","Shaoheng Fang","Zixing Lei","Yiqi Zhong","Siheng Chen"],"abstract":"Multi-agent collaborative perception could significantly upgrade the perception performance by enabling agents to share complementary information with each other through communication. It inevitably results in a fundamental trade-off between perception performance and communication bandwidth. To tackle this bottleneck issue, we propose a spatial confidence map, which reflects the spatial heterogeneity of perceptual information. It empowers agents to only share spatially sparse, yet perceptually critical information, contributing to where to communicate. Based on this novel spatial confidence map, we propose Where2comm, a communication-efficient collaborative perception framework. Where2comm has two distinct advantages: i) it considers pragmatic compression and uses less communication to achieve higher perception performance by focusing on perceptually critical areas; and ii) it can handle varying communication bandwidth by dynamically adjusting spatial areas involved in communication. To evaluate Where2comm, we consider 3D object detection in both real-world and simulation scenarios with two modalities (camera/LiDAR) and two agent types (cars/drones) on four datasets: OPV2V, V2X-Sim, DAIR-V2X, and our original CoPerception-UAVs. Where2comm consistently outperforms previous methods; for example, it achieves more than $100,000 \\times$ lower communication volume and still outperforms DiscoNet and V2X-ViT on OPV2V. Our code is available at https://github.com/MediaBrain-SJTU/where2comm.","url_abs":"https://arxiv.org/abs/2209.12836v1","url_pdf":"https://arxiv.org/pdf/2209.12836v1.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":"where2comm-communication-efficient","repo_url":"https://github.com/mediabrain-sjtu/where2comm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"3d-object-detection","task_name":"3D Object Detection"},{"task_slug":"monocular-3d-object-detection","task_name":"Monocular 3D Object Detection"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-object-detection-on-dair-v2x","task":"3D Object Detection","dataset":"DAIR-V2X","model":"Where2comm","rank_in_archive_order":2,"of":2,"metrics":{"AP50":"63.71"},"uses_additional_data":false},{"leaderboard":"/sota/3d-object-detection-on-v2x-sim","task":"3D Object Detection","dataset":"V2X-SIM","model":"Where2comm","rank_in_archive_order":5,"of":5,"metrics":{"mAOE":"0.310","mAP":"19.0","mASE":"0.275","mATE":"0.911"},"uses_additional_data":false},{"leaderboard":"/sota/monocular-3d-object-detection-on-coperception","task":"Monocular 3D Object Detection","dataset":"CoPerception-UAVs","model":"Where2comm","rank_in_archive_order":1,"of":1,"metrics":{"AP50":"65.71"},"uses_additional_data":false},{"leaderboard":"/sota/monocular-3d-object-detection-on-opv2v","task":"Monocular 3D Object Detection","dataset":"OPV2V","model":"Where2comm","rank_in_archive_order":1,"of":1,"metrics":{"AP50":"47.14"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2209.12836","atlas_url":"https://app.syntology.ai/?focus=2209.12836","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.12836"}},"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":"deterministic:regex_extraction","url":"https://github.com/MediaBrain-SJTU/where2comm","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mediabrain-sjtu/where2comm","reach":{"status":"ok"}}],"summary":{"ran":4,"unverified":2},"by_repo_kind":{"official":{"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":6,"samples":[{"code_sha256_prefix":"6f81083e2e5d4e96","entry":"AttenFusion","repo":"mediabrain-sjtu/where2comm","repo_kind":"official","path":"opencood/models/fuse_modules/where2comm_attn.py","file_url":"https://github.com/mediabrain-sjtu/where2comm/blob/HEAD/opencood/models/fuse_modules/where2comm_attn.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6f81083e2e5d4e96"}},{"code_sha256_prefix":"4ec9d4b6d8dfe0f4","entry":"Communication","repo":"mediabrain-sjtu/where2comm","repo_kind":"official","path":"opencood/models/fuse_modules/where2comm_attn.py","file_url":"https://github.com/mediabrain-sjtu/where2comm/blob/HEAD/opencood/models/fuse_modules/where2comm_attn.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":"4ec9d4b6d8dfe0f4"}},{"code_sha256_prefix":"9f94125b1d8e1caa","entry":"EncodeLayer","repo":"mediabrain-sjtu/where2comm","repo_kind":"official","path":"opencood/models/fuse_modules/where2comm_attn.py","file_url":"https://github.com/mediabrain-sjtu/where2comm/blob/HEAD/opencood/models/fuse_modules/where2comm_attn.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":"9f94125b1d8e1caa"}},{"code_sha256_prefix":"80dba65b5ece1488","entry":"ScaledDotProductAttention","repo":"mediabrain-sjtu/where2comm","repo_kind":"official","path":"opencood/models/fuse_modules/where2comm_attn.py","file_url":"https://github.com/mediabrain-sjtu/where2comm/blob/HEAD/opencood/models/fuse_modules/where2comm_attn.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"80dba65b5ece1488"}},{"code_sha256_prefix":"9b42dff7d0e05021","entry":"TransformerFusion","repo":"mediabrain-sjtu/where2comm","repo_kind":"official","path":"opencood/models/fuse_modules/where2comm_attn.py","file_url":"https://github.com/mediabrain-sjtu/where2comm/blob/HEAD/opencood/models/fuse_modules/where2comm_attn.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":"9b42dff7d0e05021"}},{"code_sha256_prefix":"d697d09dc4b0b7f4","entry":"Where2comm","repo":"mediabrain-sjtu/where2comm","repo_kind":"official","path":"opencood/models/fuse_modules/where2comm_attn.py","file_url":"https://github.com/mediabrain-sjtu/where2comm/blob/HEAD/opencood/models/fuse_modules/where2comm_attn.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":"d697d09dc4b0b7f4"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}