2023/06/26 by Mohit Vaishnav, Vaishnav, Mohit
Computer Science · #Artificial Intelligence (cs.AI) #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Symbolic Computation (cs.SC) #Visual Attention and Saliency Detection
paper · pdf · doi:10.48550/arxiv.2306.14650
openalex publication_date 2023/06/26 · openalex created_date 2023/06/28 · openalex updated_date 2026/07/28
We investigate the role of attention and memory in complex reasoning tasks. We analyze Transformer-based self-attention as a model and extend it with memory. By studying a synthetic visual reasoning test, we refine the taxonomy of reasoning tasks. Incorporating self-attention with ResNet50, we enhance feature maps using feature-based and spatial attention, achieving efficient solving of challenging visual reasoning tasks. Our findings contribute to understanding the attentional needs of SVRT tasks. Additionally, we propose GAMR, a cognitive architecture combining attention and memory, inspired by active vision theory. GAMR outperforms other architectures in sample efficiency, robustness, and compositionality, and shows zero-shot generalization on new reasoning tasks.