Qi Dou

5

Papers

7

Total Citations

Papers (5)

Boosting the visual interpretability of CLIP via adversarial fine-tuning

Hybrid Reciprocal Transformer with Triplet Feature Alignment for Scene Graph Generation

Test-Time Retrieval-Augmented Adaptation for Vision-Language Models

Structured Gradient-based Interpretations via Norm-Regularized Adversarial Training

Ensemble Diversity Facilitates Adversarial Transferability