Mimicking Human Visual Development for Learning Robust Image Representations

• URL: http://arxiv.org/abs/2512.14360v1
• Date: Tue, 16 Dec 2025 12:41:04 GMT
• Title: Mimicking Human Visual Development for Learning Robust Image Representations
• Authors: Ankita Raj, Kaashika Prajaapat, Tapan Kumar Gandhi, Chetan Arora,
• Abstract summary: We propose a progressive blurring curriculum to improve the generalization and robustness of convolutional neural networks.<n>Our approach encourages the network to prioritize global structures over high-frequency artifacts, improving robustness against distribution shifts and noisy inputs.<n>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.
• Score: 4.210503867117539
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• INDIGO+: A Unified INN-Guided Probabilistic Diffusion Algorithm for Blind and Non-Blind Image Restoration [22.19661915697775]
  We propose a novel INN-guided probabilistic diffusion algorithm for non-blind and blind image restoration.<n>INDIGO and BlindINDIGO combine the merits of the perfect reconstruction property of invertible neural networks (INN) with the strong generative capabilities of pre-trained diffusion models.
  arXiv  Detail & Related papers  (2025-01-23T18:51:52Z)
• MENTOR: Human Perception-Guided Pretraining for Increased Generalization [4.737519767218666]
  Leveraging human perception into training of convolutional neural networks (CNN) has boosted generalization capabilities of such models in open-set recognition tasks.<n>We introduce MENTOR, which addresses this question through two unique rounds of training CNNs tasked with open-set anomaly detection.<n>We show that MENTOR successfully raises the generalization performance across three different CNN backbones in a variety of anomaly detection tasks.
  arXiv  Detail & Related papers  (2023-10-30T13:50:44Z)
• Training on Foveated Images Improves Robustness to Adversarial Attacks [26.472800216546233]
  Deep neural networks (DNNs) have been shown to be vulnerable to adversarial attacks. RBlur is an image transform that simulates the loss in fidelity of peripheral vision by blurring the image and reducing its color saturation. DNNs trained on images transformed by RBlur are substantially more robust to adversarial attacks, as well as other, non-adversarial, corruptions, achieving up to 25% higher accuracy on perturbed data.
  arXiv  Detail & Related papers  (2023-08-01T21:40:30Z)
• EfficientTrain: Exploring Generalized Curriculum Learning for Training Visual Backbones [80.662250618795]
  This paper presents a new curriculum learning approach for the efficient training of visual backbones (e.g., vision Transformers) As an off-the-shelf method, it reduces the wall-time training cost of a wide variety of popular models by >1.5x on ImageNet-1K/22K without sacrificing accuracy.
  arXiv  Detail & Related papers  (2022-11-17T17:38:55Z)
• Neural Maximum A Posteriori Estimation on Unpaired Data for Motion Deblurring [87.97330195531029]
  We propose a Neural Maximum A Posteriori (NeurMAP) estimation framework for training neural networks to recover blind motion information and sharp content from unpaired data. The proposed NeurMAP is an approach to existing deblurring neural networks, and is the first framework that enables training image deblurring networks on unpaired datasets.
  arXiv  Detail & Related papers  (2022-04-26T08:09:47Z)
• Guided Interpolation for Adversarial Training [73.91493448651306]
  As training progresses, the training data becomes less and less attackable, undermining the robustness enhancement. We propose the guided framework (GIF), which employs the previous epoch's meta information to guide the data's adversarial variants. Compared with the vanilla mixup, the GIF can provide a higher ratio of attackable data, which is beneficial to the robustness enhancement.
  arXiv  Detail & Related papers  (2021-02-15T03:55:08Z)
• Image Restoration by Deep Projected GSURE [115.57142046076164]
  Ill-posed inverse problems appear in many image processing applications, such as deblurring and super-resolution. We propose a new image restoration framework that is based on minimizing a loss function that includes a "projected-version" of the Generalized SteinUnbiased Risk Estimator (GSURE) and parameterization of the latent image by a CNN.
  arXiv  Detail & Related papers  (2021-02-04T08:52:46Z)
• Encoding Robustness to Image Style via Adversarial Feature Perturbations [72.81911076841408]
  We adapt adversarial training by directly perturbing feature statistics, rather than image pixels, to produce robust models. Our proposed method, Adversarial Batch Normalization (AdvBN), is a single network layer that generates worst-case feature perturbations during training.
  arXiv  Detail & Related papers  (2020-09-18T17:52:34Z)
• Towards Achieving Adversarial Robustness by Enforcing Feature Consistency Across Bit Planes [51.31334977346847]
  We train networks to form coarse impressions based on the information in higher bit planes, and use the lower bit planes only to refine their prediction. We demonstrate that, by imposing consistency on the representations learned across differently quantized images, the adversarial robustness of networks improves significantly.
  arXiv  Detail & Related papers  (2020-04-01T09:31:10Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.