{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/af-2-s3net-attentive-feature-fusion-with","title":"(AF)2-S3Net: Attentive Feature Fusion with Adaptive Feature Selection for Sparse Semantic Segmentation Network","arxiv_id":"2102.04530","date":"2021-02-08","proceeding":null,"authors":["Ran Cheng","Ryan Razani","Ehsan Taghavi","Enxu Li","Bingbing Liu"],"abstract":"Autonomous robotic systems and self driving cars rely on accurate perception of their surroundings as the safety of the passengers and pedestrians is the top priority. Semantic segmentation is one the essential components of environmental perception that provides semantic information of the scene. Recently, several methods have been introduced for 3D LiDAR semantic segmentation. While, they can lead to improved performance, they are either afflicted by high computational complexity, therefore are inefficient, or lack fine details of smaller instances. To alleviate this problem, we propose AF2-S3Net, an end-to-end encoder-decoder CNN network for 3D LiDAR semantic segmentation. We present a novel multi-branch attentive feature fusion module in the encoder and a unique adaptive feature selection module with feature map re-weighting in the decoder. Our AF2-S3Net fuses the voxel based learning and point-based learning into a single framework to effectively process the large 3D scene. Our experimental results show that the proposed method outperforms the state-of-the-art approaches on the large-scale SemanticKITTI benchmark, ranking 1st on the competitive public leaderboard competition upon publication.","url_abs":"https://arxiv.org/abs/2102.04530v1","url_pdf":"https://arxiv.org/pdf/2102.04530v1.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":[],"tasks":[{"task_slug":"3d-semantic-segmentation","task_name":"3D Semantic Segmentation"},{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"lidar-semantic-segmentation","task_name":"LIDAR Semantic Segmentation"},{"task_slug":"segmentation","task_name":"Segmentation"},{"task_slug":"self-driving-cars","task_name":"Self-Driving Cars"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"feature-selection","task_name":"feature selection"}],"methods":[{"method_slug":"feature-selection","method_name":"Feature Selection"},{"method_slug":"sparse-convolutions","method_name":"Sparse Convolutions"},{"method_slug":"spatial-transformer","method_name":"Spatial Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-semantic-segmentation-on-semantickitti","task":"3D Semantic Segmentation","dataset":"SemanticKITTI","model":"AF2S3Net","rank_in_archive_order":11,"of":45,"metrics":{"test mIoU":"70.8%","val mIoU":"74.2%"},"uses_additional_data":true},{"leaderboard":"/sota/3d-semantic-segmentation-on-nuscenes","task":"3D Semantic Segmentation","dataset":"nuScenes","model":"AF2S3Net","rank_in_archive_order":3,"of":3,"metrics":{"mIoU":"78.3%"},"uses_additional_data":false},{"leaderboard":"/sota/lidar-semantic-segmentation-on-nuscenes","task":"LIDAR Semantic Segmentation","dataset":"nuScenes","model":"AF2S3Net","rank_in_archive_order":13,"of":36,"metrics":{"test mIoU":"0.78"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2102.04530","atlas_url":"https://app.syntology.ai/?focus=2102.04530","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2102.04530"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2102.04530\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2102.04530"},"call":"get_concepts_for_paper(arxiv_id=\"2102.04530\")"}],"by_repo":[],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":"the archive holds no code link for this paper","arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"ca538f188331f148faa5e8384c5cca63ad7d4fb9b127c7c89edc63a70ad856b8","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}