AttZoom: Attention Zoom for Better Visual Features
By: Daniel DeAlcala , Aythami Morales , Julian Fierrez and more
Potential Business Impact:
Makes computer pictures smarter at finding important details.
We present Attention Zoom, a modular and model-agnostic spatial attention mechanism designed to improve feature extraction in convolutional neural networks (CNNs). Unlike traditional attention approaches that require architecture-specific integration, our method introduces a standalone layer that spatially emphasizes high-importance regions in the input. We evaluated Attention Zoom on multiple CNN backbones using CIFAR-100 and TinyImageNet, showing consistent improvements in Top-1 and Top-5 classification accuracy. Visual analyses using Grad-CAM and spatial warping reveal that our method encourages fine-grained and diverse attention patterns. Our results confirm the effectiveness and generality of the proposed layer for improving CCNs with minimal architectural overhead.
Similar Papers
Attention Via Convolutional Nearest Neighbors
CV and Pattern Recognition
Unites two ways computers see images.
Compact Attention: Exploiting Structured Spatio-Temporal Sparsity for Fast Video Generation
CV and Pattern Recognition
Makes long videos create faster without losing quality.
Exploring Object-Aware Attention Guided Frame Association for RGB-D SLAM
CV and Pattern Recognition
Helps robots see better to map rooms.