A recurrent vision transformer shows signatures of primate visual attention
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Change DetectionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Primate-like perceptual decision making emerges through deep recurrent reinforcement learning
Progress has led to a detailed understanding of the neural mechanisms that underlie decision making in primates. However, less is known about why such mechanisms are present in the first place. Theory suggests that prima…
Reinforcement LearningDecision MakingCharacterising representation dynamics in recurrent neural networks for object recognition
Recurrent neural networks (RNNs) have yielded promising results for both recognizing objects in challenging conditions and modeling aspects of primate vision. However, the representational dynamics of recurrent computati…
Object RecognitionStable and expressive recurrent vision models
Primate vision depends on recurrent processing for reliable perception. A growing body of literature also suggests that recurrent connections improve the learning efficiency and generalization of vision models on classic…
Panoptic SegmentationLeveraging Recurrent Neural Networks for Predicting Motor Movements from Primate Motor Cortex Neural Recordings
This paper presents an efficient deep learning solution for decoding motor movements from neural recordings in non-human primates. An Autoencoder Gated Recurrent Unit (AEGRU) model was adopted as the model architecture f…
From Edges to Depth: Probing the Spatial Hierarchy in Vision Transformers
Vision Transformers trained only on image classification routinely transfer to tasks that demand spatial understanding, yet they receive no spatial supervision during pretraining. We ask where and how robustly such struc…
Image Classification