{"ID":2886475,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.03625","arxiv_id":"2508.03625","title":"AttZoom: Attention Zoom for Better Visual Features","abstract":"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.","short_abstract":"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 h...","url_abs":"https://arxiv.org/abs/2508.03625","url_pdf":"https://arxiv.org/pdf/2508.03625v1","authors":"[\"Daniel DeAlcala\",\"Aythami Morales\",\"Julian Fierrez\",\"Ruben Tolosana\"]","published":"2025-08-05T16:42:08Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.AI\"]","methods":"[\"Convolutional Neural Network\"]","has_code":false}