Pengxu Wei

16

Papers

0

Total Citations

Papers (16)

Can We Achieve Efficient Diffusion Without Self-Attention? Distilling Self-Attention into Convolutions

Delving into Cascaded Instability: A Lipschitz Continuity View on Image Restoration and Object Detection Synergy

DigitalLLaVA: Incorporating Digital Cognition Capability for Physical World Comprehension in Multimodal LLMs

Image Restoration Through Generalized Ornstein-Uhlenbeck Bridge

Kepler codebook

Min-Entropy Latent Model for Weakly Supervised Object Detection

Dual Adversarial Adaptation for Cross-Device Real-World Image Super-Resolution

Masked Images Are Counterfactual Samples for Robust Fine-Tuning

Out-of-Candidate Rectification for Weakly Supervised Semantic Segmentation

Identity-Preserving Talking Face Generation With Landmark and Appearance Priors

CDNet: Centripetal Direction Network for Nuclear Instance Segmentation

Trash To Treasure: Harvesting OOD Data With Cross-Modal Matching for Open-Set Semi-Supervised Learning

Towards Real-World Burst Image Super-Resolution: Benchmark and Method

TopoSeg: Topology-Aware Nuclear Instance Segmentation

Component Divide-and-Conquer for Real-World Image Super-Resolution

Adversarially-Aware Robust Object Detector