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

Few-shot learning (FSL) has emerged as an effective learning method and shows great
potential. Despite the recent creative works in tackling FSL tasks, learning valid information …

Visual recognition in low-data regimes requires deep neural networks to learn generalized
representations from limited training samples. Recently, CLIP-based methods have shown …

Deep networks have strong capacities of embedding data into latent representations and
finishing following tasks. However, the capacities largely come from high-quality annotated …

Dataset condensation aims at reducing the network training effort through condensing a
cumbersome training set into a compact synthetic one. State-of-the-art approaches largely …

This paper considers few-shot anomaly detection (FSAD), a practical yet under-studied
setting for anomaly detection (AD), where only a limited number of normal images are …

Abstract Vision Transformers (ViTs) emerge to achieve impressive performance on many
data-abundant computer vision tasks by capturing long-range dependencies among local …

In learning with noisy labels, the sample selection approach is very popular, which regards
small-loss data as correctly labeled during training. However, losses are generated on-the …

Real-world scenarios are usually accompanied by continuously appearing classes with
scare labeled samples, which require the machine learning model to incrementally learn …

The great success of deep learning heavily relies on increasingly larger training data, which
comes at a price of huge computational and infrastructural costs. This poses crucial …