To ensure good performance, modern machine learning models typically require large
amounts of quality annotated data. Meanwhile, the data collection and annotation processes …

We propose the first unified theoretical analysis of mixed sample data augmentation
(MSDA), such as Mixup and CutMix. Our theoretical results show that regardless of the …

Research has shown that convolutional neural networks for object recognition are
vulnerable to changes in depiction because learning is biased towards the low-level …

Recent work has shown that deep vision models tend to be overly dependent on low-level
or" texture" features, leading to poor generalization. Various data augmentation strategies …

The task of detecting small and tiny objects has not shown significant performance
improvement compared to detecting medium and large objects, even with advanced …

Low-level vision plays a crucial role in a wide range of imaging quality and image
recognition applications. However, the limited size, quality, and diversity of datasets often …

Ensuring the real-world applicability of machine learning (ML) models poses a primary
challenge, namely, the ability to generalize effectively to unseen scenarios encountered …