Mimicking Human Visual Development for Learning Robust Image Representations

TL;DR

Inspired by human visual development, a progressive blurring curriculum for CNN training improves robustness and generalization by mimicking infant visual acuity growth, reducing distribution shift errors.

Contribution

We introduce a structured progressive blurring training curriculum that enhances CNN robustness and generalization, inspired by human visual development, outperforming static augmentation methods.

Findings

Reduces mean corruption error by up to 8.30% on CIFAR-10-C

Improves robustness on ImageNet-100-C datasets

Enhances adversarial robustness and complements existing augmentations

Abstract

The human visual system is remarkably adept at adapting to changes in the input distribution; a capability modern convolutional neural networks (CNNs) still struggle to match. Drawing inspiration from the developmental trajectory of human vision, we propose a progressive blurring curriculum to improve the generalization and robustness of CNNs. Human infants are born with poor visual acuity, gradually refining their ability to perceive fine details. Mimicking this process, we begin training CNNs on highly blurred images during the initial epochs and progressively reduce the blur as training advances. This approach encourages the network to prioritize global structures over high-frequency artifacts, improving robustness against distribution shifts and noisy inputs. Challenging prior claims that blurring in the initial training epochs imposes a stimulus deficit and irreversibly harms model performance, we reveal that early-stage blurring enhances generalization with minimal impact on in-domain accuracy. Our experiments demonstrate that the proposed curriculum reduces mean corruption error (mCE) by up to 8.30% on CIFAR-10-C and 4.43% on ImageNet-100-C datasets, compared to standard training without blurring. Unlike static blur-based augmentation, which applies blurred images randomly throughout training, our method follows a structured progression, yielding consistent gains across various datasets. Furthermore, our approach complements other augmentation techniques, such as CutMix and MixUp, and enhances both natural and adversarial robustness against common attack methods. Code is available at https://github.com/rajankita/Visual_Acuity_Curriculum.