Text Generation aims to produce plausible and readable text in human language from input
data. The resurgence of deep learning has greatly advanced this field, in particular, with the …

Deep classifier neural networks enter the terminal phase of training (TPT) when training
error reaches zero and tend to exhibit intriguing Neural Collapse (NC) properties. Neural …

Emerging interests have been brought to recognize previously unseen objects given very
few training examples, known as few-shot object detection (FSOD). Recent researches …

Contrastive learning applied to self-supervised representation learning has seen a
resurgence in recent years, leading to state of the art performance in the unsupervised …

State-of-the-art natural language understanding classification models follow two-stages: pre-
training a large language model on an auxiliary task, and then fine-tuning the model on a …

Generalization of deep networks has been of great interest in recent years, resulting in a
number of theoretically and empirically motivated complexity measures. However, most …

Semantic segmentation of LiDAR point clouds is an important task in autonomous driving.
However, training deep models via conventional supervised methods requires large …

Few-shot class-incremental learning (FSCIL) aims at learning to classify new classes
continually from limited samples without forgetting the old classes. The mainstream …

Collecting labeled data for the task of semantic segmentation is expensive and time-
consuming, as it requires dense pixel-level annotations. While recent Convolutional Neural …

Diabetic Retinopathy (DR) is a major complication in human eyes among the diabetic
patients. Early detection of the DR can save many patients from permanent blindness …