Minghao Fu

9

Papers

39

Total Citations

Papers (9)

DTL: Disentangled Transfer Learning for Visual Recognition

Instance-based Max-margin for Practical Few-shot Recognition

CHATS: Combining Human-Aligned Optimization and Test-Time Sampling for Text-to-Image Generation

Rectify the Regression Bias in Long-Tailed Object Detection

Quantization without Tears

Worst Case Matters for Few-Shot Recognition

Minimal Interaction Seperated Tuning: A New Paradigm for Visual Adaptation

TeEFusion: Blending Text Embeddings to Distill Classifier-Free Guidance

Multi-Label Self-Supervised Learning with Scene Images