Methods › Computer Vision › Feature Extractors › NEAT

Neural Attention Fields

NEAT

25 papers tagged archive 2025-07-28

archive 2025-07-28 Description, source and code snippet are the archive's method entry.

NEAT, or Neural Attention Fields, is a feature representation 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 the 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. Furthermore, visualizing the attention maps for models with NEAT intermediate representations provides improved interpretability.

Source: NEAT: Neural Attention Fields for End-to-End Autonomous Driving

Papers archive 2025-07-28

25 shown of 25, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.

Tasks archive 2025-07-28

20 shown of 37 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.

TaskPapers
Computational Efficiency3
GPU3
Reinforcement Learning3
reinforcement-learning3
Binary Classification2
Deep Reinforcement Learning2
Novel View Synthesis2
Q-Learning2
Reinforcement Learning (RL)2
3D Reconstruction1
3D Wireframe Reconstruction1
Active Learning1
Articles1
Atari Games1
Autonomous Driving1
Autonomous Navigation1
Binarization1
CARLA longest61
Classification1
Decision Making1

Usage over time archive 2025-07-28

Papers per year tagged with NEAT: 2021 to 2025, peak 6 6 0 2021: 3 papers 2021 2022: 5 papers 2022 2023: 5 papers 2023 2024: 6 papers 2024 2025: 6 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (25 dated). Bars are counts, not a trend claim.

Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).

Categories archive 2025-07-28

Feature Extractors

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections