5 papers
Let ViT Speak: Generative Language-Image Pre-training
Yan Fang, Mengcheng Lan, Zilong Huang +7
In this paper, we present \textbf{Gen}erative \textbf{L}anguage-\textbf{I}mage \textbf{P}re-training (GenLIP), a minimalist generative pretraining framework for Vision Transformers…
PreFM: Online Audio-Visual Event Parsing via Predictive Future Modeling
Xiao Yu, Yan Fang, Xiaojie Jin +2
Audio-visual event parsing plays a crucial role in understanding multimodal video content, but existing methods typically rely on offline processing of entire videos with huge mode…
Harnessing Group-Oriented Consistency Constraints for Semi-Supervised Semantic Segmentation in CdZnTe Semiconductors
Peihao Li, Yan Fang, Man Liu +4
Labeling Cadmium Zinc Telluride (CdZnTe) semiconductor images is challenging due to the low-contrast defect boundaries, necessitating annotators to cross-reference multiple views.…
SAGE: Exploring the Boundaries of Unsafe Concept Domain with Semantic-Augment Erasing
Hongguang Zhu, Yunchao Wei, Mengyu Wang +4
Diffusion models (DMs) have achieved significant progress in text-to-image generation. However, the inevitable inclusion of sensitive information during pre-training poses safety r…
IPSeg: Image Posterior Mitigates Semantic Drift in Class-Incremental Segmentation
Xiao Yu, Yan Fang, Yao Zhao +1
Class incremental learning aims to enable models to learn from sequential, non-stationary data streams across different tasks without catastrophic forgetting. In class incremental…