As for few-shot image classification, recently, some works revisit the standard transfer
learning paradigm, ie, pre-training and fine-tuning, and have achieved some success …

Few-shot segmentation focuses on the generalization of models to segment unseen object
with limited annotated samples. However, existing approaches still face two main …

Adversarial attacks aim to disturb the functionality of a target system by adding specific noise
to the input samples, bringing potential threats to security and robustness when applied to …

The use of pre-training is an emerging technique to enhance a neural model's performance,
which has been shown to be effective for many neural language models such as BERT. This …

In recent years, deep neural networks have emerged as a dominant machine learning tool
for a wide variety of application fields. Due to the expensive cost of manual labeling efforts, it …

Compositional Zero-Shot Learning (CZSL) aims to recognize novel concepts from known
sub-concepts. However, it is still challenging since the intricate interaction between sub …

Face recognition models that utilize deep learning techniques can be easily targeted by
adversarial attacks. In order to detect these attacks, the majority of detection methods focus …

Many existing graph-based methods for few-shot learning problem focused on either
separately learning node features or edge features or simply utilizing graph convolution …

Few-shot object detection (FSOD) aims at heuristically detecting novel objects with limited
labeled data. Typical methods focus on the advanced classifications using the features …