A recurrent vision transformer shows signatures of primate visual attention
원문 초록
Attention is fundamental to both biological and artificial intelligence, yet research on animal attention and AI self attention remains largely disconnected. We propose a Recurrent Vision Transformer (Recurrent ViT) that integrates self-attention with recurrent memory, allowing both current inputs and stored information to guide attention allocation. Trained solely via sparse reward feedback on a spatially cued orientation change detection task, a paradigm used in primate studies, our model exhibits primate like signatures of attention, including improved accuracy and faster responses for cued stimuli that scale with cue validity. Analysis of self-attention maps reveals dynamic spatial prioritization with reactivation prior to expected changes, and targeted perturbations produce performance shifts similar to those observed in primate frontal eye fields and superior colliculus. These findings demonstrate that incorporating recurrent feedback into self attention can capture key aspects of primate visual attention.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Precision Spatio-Temporal Feature Fusion for Robust Remote Sensing Change Detection
Be the Change You Want to See: Revisiting Remote Sensing Change Detection Practices
HydroChronos: Forecasting Decades of Surface Water Change
Temporal-Spectral-Spatial Unified Remote Sensing Dense Prediction
Non-Registration Change Detection: A Novel Change Detection Task and Benchmark Dataset
Building-Guided Pseudo-Label Learning for Cross-Modal Building Damage Mapping
토론
이 논문과 연결된 포럼 글이 아직 없습니다.