Despite the remarkable performance that modern deep neural networks have achieved on
independent and identically distributed (IID) data, they can crash under distribution shifts …

This work focuses on the potential of Vision LLMs (VLLMs) in visual reasoning. Different
from prior studies, we shift our focus from evaluating standard performance to introducing a …

Practical object detection application can lose its effectiveness on image inputs with natural
distribution shifts. This problem leads the research community to pay more attention on the …

When deployed on a new domain different from the training set, deep learning often suffers
from severe performance degradation. To combat domain shift, domain adaptation and …

Industrial anomaly detection (IAD) is crucial for automating industrial quality inspection. The
diversity of the datasets is the foundation for developing comprehensive IAD algorithms …

Current benchmarks for assessing vision-language models (VLMs) often focus on their
perception or problem-solving capabilities and neglect other critical aspects such as …

Multi-modal large language models (MLLMs) are trained based on large language models
(LLM), with an enhanced capability to comprehend multi-modal inputs and generate textual …

Deep learning for unsupervised image segmentation remains challenging due to the
absence of human labels. The common idea is to train a segmentation head, with the …

Enhancing the robustness of vision algorithms in real-world scenarios is challenging. One
reason is that existing robustness benchmarks are limited, as they either rely on synthetic …

Since real-world training datasets cannot properly sample the long tail of the underlying data
distribution, corner cases and rare out-of-domain samples can severely hinder the …