Visual representation learning is ubiquitous in various real-world applications, including
visual comprehension, video understanding, multi-modal analysis, human-computer …

Prompting a pretrained language model with natural language patterns has been proved
effective for natural language understanding (NLU). However, our preliminary study reveals …

The trustworthiness of machine learning has emerged as a critical topic in the field,
encompassing various applications and research areas such as robustness, security …

As the class size grows, maintaining a balanced dataset across many classes is challenging
because the data are long-tailed in nature; it is even impossible when the sample-of-interest …

We present a causal inference framework to improve Weakly-Supervised Semantic
Segmentation (WSSS). Specifically, we aim to generate better pixel-level pseudo-masks by …

Few-shot class-incremental learning (FSCIL) aims to design machine learning algorithms
that can continually learn new concepts from a few data points, without forgetting knowledge …

This paper considers incremental few-shot learning, which requires a model to continually
recognize new categories with only a few examples provided. Our study shows that existing …

Existing visual question answering methods often suffer from cross-modal spurious
correlations and oversimplified event-level reasoning processes that fail to capture event …

In few-shot learning scenarios, the challenge is to generalize and perform well on new
unseen examples when only very few labeled examples are available for each task. Model …

Recent VQA models may tend to rely on language bias as a shortcut and thus fail to
sufficiently learn the multi-modal knowledge from both vision and language. In this paper …