3 papers
cs.CV2025
Images Speak Louder Than Scores: Failure Mode Escape for Enhancing Generative Quality
Jie Shao, Ke Zhu, Minghao Fu +2
Diffusion models have achieved remarkable progress in class-to-image generation. However, we observe that despite impressive FID scores, state-of-the-art models often generate dist…
cs.CV2025
Quantization without Tears
Minghao Fu, Hao Yu, Jie Shao +3
Deep neural networks, while achieving remarkable success across diverse tasks, demand significant resources, including computation, GPU memory, bandwidth, storage, and energy. Netw…
cs.CV2025
All You Need in Knowledge Distillation Is a Tailored Coordinate System
Junjie Zhou, Ke Zhu, Jianxin Wu
Knowledge Distillation (KD) is essential in transferring dark knowledge from a large teacher to a small student network, such that the student can be much more efficient than the t…