Generalization to novel visual conditions remains a central challenge for both human and machine vision, yet standard robustness metrics offer limited insight into how systems trade accuracy for robustness. We introduce a rate-distortion-theoretic framework that treats stimulus-response behavior as an effective communication channel, derives rate-distortion (RD) frontiers from confusion matrices, and summarizes each system with two interpretable geometric signatures - slope ($β$) and curvature ($κ$) - which capture the marginal cost and abruptness of accuracy-robustness trade-offs. Applying this framework to human psychophysics and 18 deep vision models under controlled image perturbations, we compare generalization geometry across model architectures and training regimes. We find that both biological and artificial systems follow a common lossy-compression principle but occupy systematically different regions of RD space. In particular, humans exhibit smoother, more flexible trade-offs, whereas modern deep networks operate in steeper and more brittle regimes even at matched accuracy. Across training regimes, robustness training induces systematic but dissociable shifts in beta/kappa, revealing cases where improved robustness or accuracy does not translate into more human-like generalization geometry. These results demonstrate that RD geometry provides a compact, model-agnostic lens for comparing generalization behavior across systems beyond standard accuracy-based metrics.

翻译：泛化到新的视觉条件仍然是人类与机器视觉面临的核心挑战，然而标准的鲁棒性指标难以深入揭示系统如何在准确性与鲁棒性之间进行权衡。本文引入一个速率-失真理论框架，将刺激-响应行为视为一个有效通信信道，从混淆矩阵推导出速率-失真（RD）前沿，并通过两个可解释的几何特征——斜率（β）和曲率（κ）——来概括每个系统的特性，这两个特征分别捕捉了准确性-鲁棒性权衡的边际成本与突变性。将该框架应用于人类心理物理学实验和18个深度视觉模型在受控图像扰动下的表现，我们比较了不同模型架构与训练机制下的泛化几何特性。研究发现，生物与人工系统均遵循有损压缩的共同原理，但占据着速率-失真空间中系统性的不同区域。具体而言，人类表现出更平滑、更灵活的权衡特性，而现代深度网络即使在匹配的准确性水平下，仍处于更陡峭、更脆弱的权衡状态。在不同训练机制中，鲁棒性训练会引起β/κ的系统性但可分离的偏移，揭示了在某些情况下，鲁棒性或准确性的提升并未转化为更接近人类的泛化几何特性。这些结果表明，速率-失真几何为比较不同系统的泛化行为提供了一个超越标准准确性指标的紧凑且与模型无关的分析视角。