{"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/neat-neural-attention-fields-for-end-to-end","title":"NEAT: Neural Attention Fields for End-to-End Autonomous Driving","arxiv_id":"2109.04456","date":"2021-09-09","proceeding":"ICCV 2021 10","authors":["Kashyap Chitta","Aditya Prakash","Andreas Geiger"],"abstract":"Efficient reasoning about the semantic, spatial, and temporal structure of a scene is a crucial prerequisite for autonomous driving. We present NEural ATtention fields (NEAT), a novel representation that enables such reasoning for end-to-end imitation learning models. NEAT is a continuous function which maps locations in Bird's Eye View (BEV) scene coordinates to waypoints and semantics, using intermediate attention maps to iteratively compress high-dimensional 2D image features into a compact representation. This allows our model to selectively attend to relevant regions in the input while ignoring information irrelevant to the driving task, effectively associating the images with the BEV representation. In a new evaluation setting involving adverse environmental conditions and challenging scenarios, NEAT outperforms several strong baselines and achieves driving scores on par with the privileged CARLA expert used to generate its training data. Furthermore, visualizing the attention maps for models with NEAT intermediate representations provides improved interpretability.","url_abs":"https://arxiv.org/abs/2109.04456v1","url_pdf":"https://arxiv.org/pdf/2109.04456v1.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":"neat-neural-attention-fields-for-end-to-end","repo_url":"https://github.com/autonomousvision/neat","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"autonomous-driving","task_name":"Autonomous Driving"},{"task_slug":"carla-longest6","task_name":"CARLA longest6"},{"task_slug":"imitation-learning","task_name":"Imitation Learning"},{"task_slug":"novel-view-synthesis","task_name":"Novel View Synthesis"}],"methods":[{"method_slug":"carla","method_name":"CARLA"},{"method_slug":"entropy-regularization","method_name":"Entropy Regularization"},{"method_slug":"neat","method_name":"NEAT"},{"method_slug":"ppo","method_name":"PPO"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/autonomous-driving-on-carla-leaderboard","task":"Autonomous Driving","dataset":"CARLA Leaderboard","model":"NEAT","rank_in_archive_order":15,"of":18,"metrics":{"Driving Score":"21.83","Infraction penalty":"0.65","Route Completion":"41.71"},"uses_additional_data":false},{"leaderboard":"/sota/carla-longest6-on-carla","task":"CARLA longest6","dataset":"CARLA","model":"Neural Attention Fields (NEAT)","rank_in_archive_order":19,"of":21,"metrics":{"Driving Score":"24","Infraction Score":"0.71","Route Completion":"62"},"uses_additional_data":false},{"leaderboard":"/sota/novel-view-synthesis-on-x3d","task":"Novel View Synthesis","dataset":"X3D","model":"NeAT","rank_in_archive_order":4,"of":6,"metrics":{"PSNR":"36.01","SSIM":"0.9638"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2109.04456","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2109.04456"}},"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/autonomousvision/neat","reach":null}],"summary":{"unverified":2},"by_repo_kind":{"official":{"samples":2,"ran":0,"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":"f03a0d1e4f3c29b0","entry":"Encoder","repo":"autonomousvision/neat","repo_kind":"official","path":"neat/architectures/encoder.py","file_url":"https://github.com/autonomousvision/neat/blob/HEAD/neat/architectures/encoder.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f03a0d1e4f3c29b0"}},{"code_sha256_prefix":"1a6e75ebc48fec81","entry":"ImageCNN","repo":"autonomousvision/neat","repo_kind":"official","path":"neat/architectures/encoder.py","file_url":"https://github.com/autonomousvision/neat/blob/HEAD/neat/architectures/encoder.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1a6e75ebc48fec81"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}