5 citations · 8 across the 16 of their papers we have counts for
6 papers · 1 filter
SAFE: Slow and Fast Parameter-Efficient Tuning for Continual Learning with Pre-Trained Models
Linglan Zhao, Xuerui Zhang, Ke Yan +2
Continual learning aims to incrementally acquire new concepts in data streams while resisting forgetting previous knowledge. With the rise of powerful pre-trained models (PTMs), th…
Fuse Before Transfer: Knowledge Fusion for Heterogeneous Distillation
Guopeng Li, Qiang Wang, Ke Yan +3
Most knowledge distillation (KD) methodologies predominantly focus on teacher-student pairs with similar architectures, such as both being convolutional neural networks (CNNs). How…
Dual Relation Mining Network for Zero-Shot Learning
Jinwei Han, Yingguo Gao, Zhiwen Lin +4
Zero-shot learning (ZSL) aims to recognize novel classes through transferring shared semantic knowledge (e.g., attributes) from seen classes to unseen classes. Recently, attention-…
Anchor-based Robust Finetuning of Vision-Language Models
Jinwei Han, Zhiwen Lin, Zhongyisun Sun +5
We aim at finetuning a vision-language model without hurting its out-of-distribution (OOD) generalization. We address two types of OOD generalization, i.e., i) domain shift such as…
LaRE: Latent Reconstruction Error Based Method for Diffusion-Generated Image Detection
Yunpeng Luo, Junlong Du, Ke Yan +1
The evolution of Diffusion Models has dramatically improved image generation quality, making it increasingly difficult to differentiate between real and generated images. This deve…
Model Tailor: Mitigating Catastrophic Forgetting in Multi-modal Large Language Models
Didi Zhu, Zhongyi Sun, Zexi Li +5
Catastrophic forgetting emerges as a critical challenge when fine-tuning multi-modal large language models (MLLMs), where improving performance on unseen tasks often leads to a sig…