Showing cs.CVShow all
3 papers · 1 filter
cs.CV2025
Hierarchical Feature-level Reverse Propagation for Post-Training Neural Networks
Ni Ding, Lei He, Shengbo Eben Li +1
End-to-end autonomous driving has emerged as a dominant paradigm, yet its highly entangled black-box models pose significant challenges in terms of interpretability and safety assu…
cs.CV2025
Post-Training Quantization for Diffusion Transformer via Hierarchical Timestep Grouping
Ning Ding, Jing Han, Yuchuan Tian +3
Diffusion Transformer (DiT) has now become the preferred choice for building image generation models due to its great generation capability. Unlike previous convolution-based UNet…
cs.CV2025
GPT4Image: Large Pre-trained Models Help Vision Models Learn Better on Perception Task
Ning Ding, Yehui Tang, Zhongqian Fu +3
The upsurge in pre-trained large models started by ChatGPT has swept across the entire deep learning community. Such powerful models demonstrate advanced generative ability and mul…