3 papers
cs.CV2025
Semantic-Space-Intervened Diffusive Alignment for Visual Classification
Zixuan Li, Lei Meng, Guoqing Chao +5
Cross-modal alignment is an effective approach to improving visual classification. Existing studies typically enforce a one-step mapping that uses deep neural networks to project t…
cs.CV2025
Empowering Vision Transformers with Multi-Scale Causal Intervention for Long-Tailed Image Classification
Xiaoshuo Yan, Zhaochuan Li, Lei Meng +4
Causal inference has emerged as a promising approach to mitigate long-tail classification by handling the biases introduced by class imbalance. However, along with the change of ad…
cs.CV2025
Global Intervention and Distillation for Federated Out-of-Distribution Generalization
Zhuang Qi, Runhui Zhang, Lei Meng +3
Attribute skew in federated learning leads local models to focus on learning non-causal associations, guiding them towards inconsistent optimization directions, which inevitably re…