4 papers
Switch-KD: Visual-Switch Knowledge Distillation for Vision-Language Models
Haoyi Sun, Xiaoxiao Wang, Ning Mao +5
Vision-Language Models (VLMs) have shown remarkable capabilities in joint vision-language understanding, but their large scale poses significant challenges for deployment in resour…
Noise Diffusion for Enhancing Semantic Faithfulness in Text-to-Image Synthesis
Boming Miao, Chunxiao Li, Xiaoxiao Wang +4
Diffusion models have achieved impressive success in generating photorealistic images, but challenges remain in ensuring precise semantic alignment with input prompts. Optimizing t…
Bridging the Gap Between Ideal and Real-world Evaluation: Benchmarking AI-Generated Image Detection in Challenging Scenarios
Chunxiao Li, Xiaoxiao Wang, Meiling Li +5
With the rapid advancement of generative models, highly realistic image synthesis has posed new challenges to digital security and media credibility. Although AI-generated image de…
An Efficient Framework for Enhancing Discriminative Models via Diffusion Techniques
Chunxiao Li, Xiaoxiao Wang, Boming Miao +3
Image classification serves as the cornerstone of computer vision, traditionally achieved through discriminative models based on deep neural networks. Recent advancements have intr…