Lei Feng

19

Papers

55

Total Citations

Papers (19)

Investigating and Mitigating the Side Effects of Noisy Views for Self-Supervised Clustering Algorithms in Practical Multi-View Scenarios

Rethinking Chain-of-Thought from the Perspective of Self-Training

Attribute-based Visual Reprogramming for Vision-Language Models

Test-Time Multimodal Backdoor Detection by Contrastive Prompting

Representation Surgery in Model Merging with Probabilistic Modeling

Robust Node Classification on Graph Data with Graph and Label Noise

Positive-Unlabeled Learning by Latent Group-Aware Meta Disambiguation

Targeted Representation Alignment for Open-World Semi-Supervised Learning

Visual-Text Cross Alignment: Refining the Similarity Score in Vision-Language Models

Influence-Based Fair Selection for Sample-Discriminative Backdoor Attack

Enhancing the Influence of Labels on Unlabeled Nodes in Graph Convolutional Networks

Improving Generalization of Deep Neural Networks by Optimum Shifting

Sample-specific Masks for Visual Reprogramming-based Prompting

A General Framework for Learning from Weak Supervision

Positive and Unlabeled Learning with Controlled Probability Boundary Fence

Candidate Pseudolabel Learning: Enhancing Vision-Language Models by Prompt Tuning with Unlabeled Data

Exploiting Human-AI Dependence for Learning to Defer

Mitigating Privacy Risk in Membership Inference by Convex-Concave Loss

CroSel: Cross Selection of Confident Pseudo Labels for Partial-Label Learning