Contrastive Learning has recently received interest due to its success in self-supervised
representation learning in the computer vision domain. However, the origins of Contrastive …

Metric learning aims to measure the similarity among samples while using an optimal
distance metric for learning tasks. Metric learning methods, which generally use a linear …

Cutting-edge diffusion models produce images with high quality and customizability,
enabling them to be used for commercial art and graphic design purposes. But do diffusion …

Fine-grained image analysis (FGIA) is a longstanding and fundamental problem in computer
vision and pattern recognition, and underpins a diverse set of real-world applications. The …

While semantic communications have shown the potential in the case of single-modal single-
users, its applications to the multi-user scenario remain limited. In this paper, we investigate …

In this paper, an ill-posed problem of multiple adverse weather removal is investigated. Our
goal is to train a model with a'unified'architecture and only one set of pretrained weights that …

Deep classifiers have achieved great success in visual recognition. However, real-world
data is long-tailed by nature, leading to the mismatch between training and testing …

Recently, deep learned enabled end-to-end communication systems have been developed
to merge all physical layer blocks in the traditional communication systems, which make joint …

This paper provides a pair similarity optimization viewpoint on deep feature learning, aiming
to maximize the within-class similarity s_p and minimize the between-class similarity s_n …

The long-tail distribution of the visual world poses great challenges for deep learning based
classification models on how to handle the class imbalance problem. Existing solutions …