Abstract
Contemporary deep learning models have achieved impressive performance in image classification by primarily leveraging statistical regularities within large datasets, but they rarely incorporate structured insights drawn directly from perceptual psychology. To explore the potential of perceptually motivated inductive biases, we propose integrating classic geometric visual illusions well-studied phenomena from human perception into standard image-classification training pipelines. Specifically, we introduce a synthetic, parametric geometric-illusion dataset and evaluate three multi-source learning strategies that combine illusion recognition tasks with ImageNet classification objectives. Our experiments reveal two key conceptual insights: (i) incorporating geometric illusions as auxiliary supervision systematically improves generalization, especially in visually challenging cases involving intricate contours and fine textures; and (ii) perceptually driven inductive biases, even when derived from synthetic stimuli traditionally considered unrelated to natural image recognition, can enhance the structural sensitivity of both CNN and transformer-based architectures. These results demonstrate a novel integration of perceptual science and machine learning and suggest new directions for embedding perceptual priors into vision model design.
Abstract (translated)
现代深度学习模型通过主要利用大规模数据集中的统计规律，在图像分类任务中取得了令人印象深刻的表现，但这些模型很少直接采用从感知心理学中提取的结构化见解。为了探索由感知动机推导出的归纳偏置（inductive biases）的潜力，我们提出将经典的几何视觉错觉——即人类知觉中的经典现象——整合到标准图像分类训练流程中。具体来说，我们引入了一个合成、参数化的几何错觉数据集，并评估了三种多源学习策略，这些策略结合了对几何错觉任务的认识和ImageNet分类目标。 我们的实验揭示了两个关键概念性见解： (i) 将几何错觉作为辅助监督系统地提高了泛化能力，在涉及复杂轮廓和精细纹理的视觉挑战性案例中尤其明显； (ii) 即使源自于传统上被认为与自然图像识别无关的人工刺激物，感知驱动的归纳偏置也能增强基于卷积神经网络（CNN）和变换器架构的模型在结构敏感度上的表现。 这些结果展示了将感知科学与机器学习结合的新颖方法，并为将知觉先验嵌入视觉模型设计中提供了新的方向。
URL
https://arxiv.org/abs/2509.15156
