7 papers · 1 filter
Efficient and High-Quality Depth Estimation via Pixel-Space Diffusion with Linear Attention
Bingde Liu, Wu Ran, Jinglei Zhang +2
This work presents , a inear-ttention-based xel-pace generative framework that achieves efficient and high-fidelity…
ACE-LoRA: Adaptive Orthogonal Decoupling for Continual Image Editing
Yuehao Liu, Weijia Zhang, Xuanming Shang +4
State-of-the-art diffusion models often rely on parameter-efficient fine-tuning to perform specialized image editing tasks. However, real-world applications require continual adapt…
Guiding a Diffusion Model by Swapping Its Tokens
Weijia Zhang, Yuehao Liu, Shanyan Guan +4
Classifier-Free Guidance (CFG) is a widely used inference-time technique to boost the image quality of diffusion models. Yet, its reliance on text conditions prevents its use in un…
Cross-Architecture Distillation Made Simple with Redundancy Suppression
Weijia Zhang, Yuehao Liu, Wu Ran +1
We describe a simple method for cross-architecture knowledge distillation, where the knowledge transfer is cast into a redundant information suppression formulation. Existing metho…
VRM: Knowledge Distillation via Virtual Relation Matching
Weijia Zhang, Fei Xie, Weidong Cai +1
Knowledge distillation (KD) aims to transfer the knowledge of a more capable yet cumbersome teacher model to a lightweight student model. In recent years, relation-based KD methods…
CP-VoteNet: Contrastive Prototypical VoteNet for Few-Shot Point Cloud Object Detection
Xuejing Li, Weijia Zhang, Chao Ma
Few-shot point cloud 3D object detection (FS3D) aims to identify and localise objects of novel classes from point clouds, using knowledge learnt from annotated base classes and nov…