The" pre-training-downstream adaptation" presents both new opportunities and challenges
for Continual Learning (CL). Although the recent state-of-the-art in CL is achieved through …

Transfer learning has recently become the dominant paradigm of machine learning. Pre-
trained models fine-tuned for downstream tasks achieve better performance with fewer …

The advent of foundation models, which are pre-trained on vast datasets, has ushered in a
new era of computer vision, characterized by their robustness and remarkable zero-shot …

Although the applications of artificial intelligence especially deep learning have greatly
improved various aspects of intelligent manufacturing, they still face challenges for broader …

In line with the development of Industry 4.0, surface defect detection/anomaly detection
becomes a topical subject in the industry field. Improving efficiency as well as saving labor …

With the continuous improvement of computing power and deep learning algorithms in
recent years, the foundation model has grown in popularity. Because of its powerful …

In this work, we introduce MDL-NAS, a unified framework that integrates multiple vision tasks
into a manageable supernet and optimizes these tasks collectively under diverse dataset …

Visual programming, a modular paradigm, integrates different modules and Python
operators to solve various vision-language tasks. Unlike end-to-end models that need task …

Abstract Neural Architecture Search (NAS) aims at identifying the optimal network
architecture for a specific need in an automated manner, which serves as an alternative to …

The completion of large occluded human body images poses a unique challenge for
general image completion methods. The complex shape variations of human bodies make it …