Latent Noise Segmentation: How Neural Noise Leads to the Emergence of Segmentation and Grouping

no code implementations • 28 Sep 2023 • Ben Lonnqvist, Zhengqing Wu, Michael H. Herzog

Humans are able to segment images effortlessly without supervision using perceptual grouping.

Segmentation Semantic Segmentation

Frequency-Based Vulnerability Analysis of Deep Learning Models against Image Corruptions

1 code implementation • 12 Jun 2023 • Harshitha Machiraju, Michael H. Herzog, Pascal Frossard

In response, researchers have developed image corruption datasets to evaluate the performance of deep neural networks in handling such corruptions.

Classification Robust classification

A comment on Guo et al. [arXiv:2206.11228]

no code implementations • 2 Aug 2022 • Ben Lonnqvist, Harshitha Machiraju, Michael H. Herzog

In a recent article, Guo et al. [arXiv:2206. 11228] report that adversarially trained neural representations in deep networks may already be as robust as corresponding primate IT neural representations.

Empirical Advocacy of Bio-inspired Models for Robust Image Recognition

1 code implementation • 18 May 2022 • Harshitha Machiraju, Oh-Hyeon Choung, Michael H. Herzog, Pascal Frossard

There are continuous attempts to use features of the human visual system to improve the robustness of neural networks to data perturbations.

Data Augmentation