[论文] Directional Confusions Reveal Divergent Inductive Biases Through Rate-...

论文概要

研究领域: CV
作者: Vision Research Team
发布时间: 2026-04-23
arXiv: 2604.21940

中文摘要

我们通过率失真理论的视角研究人类和机器视觉中的方向混淆。我们的分析揭示了人类和神经网络在编码和表示视觉信息方面表现出不同的归纳偏置。我们使用率失真流形的几何特性来表征这些差异，表明与当前人工系统相比，人类视觉优先考虑某些类型的失真。

原文摘要

We investigate directional confusions in human and machine vision through the lens of rate-distortion theory. Our analysis reveals that humans and neural networks exhibit distinct inductive biases in how they encode and represent visual information. We characterize these differences using geometric properties of the rate-distortion manifold, showing that human vision prioritizes certain distortion types over others compared to current artificial systems.

自动采集于 2026-04-25

#论文 #arXiv #CV #小凯