← Search

Chun Tong Lei

2 accepted papers

2025

Instant Adversarial Purification with Adversarial Consistency Distillation

CVPR 2025poster

Neural networks have revolutionized numerous fields with their exceptional performance, yet they remain susceptible to adversarial attacks through subtle perturbations. While diffusion-based purification methods like DiffPure offer promising defense mechanisms, their computational overhead presents…

Cited by 4SourcePDFScholar
2025

T2ICount: Enhancing Cross-modal Understanding for Zero-Shot Counting

CVPR 2025highlight

Zero-shot object counting aims to count instances of arbitrary object categories specified by text descriptions. Existing methods typically rely on vision-language models like CLIP, but often exhibit limited sensitivity to text prompts. We present T2ICount, a diffusion-based framework that leverages…