视网膜视区化改进卷积神经网络的分类与定位
Foveated Retinotopy Improves Classification and Localization in Convolutional Neural Networks
AI总结：
视网膜视区化改进CNN分类与定位性能，增强鲁棒性与显著性图生成。
摘要：
从鹰发现猎物到人类识别面孔，快速的视觉能力依赖于视网膜视区组织，这种组织在中央视觉提供高清晰度的同时保持外围的低分辨率。这种组织在早期视觉通路中得到保留，但在机器学习中仍被忽视。本文探讨如何将视网膜视区变换作为预处理层嵌入到卷积神经网络（CNN）中，以提高图像分类的性能。通过将对数极坐标映射应用于现成模型并重新训练它们，我们保持了相当的准确性，同时提高了对尺度和旋转的鲁棒性。我们证明了这种架构对注视点位移高度敏感，这种敏感性可以作为定义显著性图的代理，有效促进物体定位。我们的结果表明，视网膜视区化编码了先验几何知识，为视觉搜索提供了解决方案，并增强了分类和定位。这些发现将生物视觉原理与人工网络联系起来，指出了计算机视觉系统的新、稳健和高效的方向。
英文摘要：
From falcons spotting preys to humans recognizing faces, rapid visual abilities depend on a foveated retinal organization which delivers high-acuity central vision while preserving low-resolution periphery. This organization is conserved along early visual pathways but remains underexplored in machine learning. Here we examine how embedding a foveated retinotopic transformation as a preprocessing layer impacts convolutional neural networks (CNNs) for image classification. By applying a log-polar mapping to off-the-shelf models and retraining them, we retain comparable accuracy while improving robustness to scale and rotation. We show that this architecture becomes highly sensitive to fixation-point shifts, and that this sensitivity yields a proxy for defining saliency maps that effectively facilitates object localization. Our results show that foveated retinotopy encodes prior geometric knowledge, offering a solution to visual-search and enhancing both classification and localization. These findings connect biological vision principles with artificial networks, pointing to new, robust and efficient directions for computer-vision systems.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
