Alert button
Picture for Beier Zhu

Beier Zhu

Alert button

Generalized Logit Adjustment: Calibrating Fine-tuned Models by Removing Label Bias in Foundation Models

Oct 12, 2023
Beier Zhu, Kaihua Tang, Qianru Sun, Hanwang Zhang

Figure 1 for Generalized Logit Adjustment: Calibrating Fine-tuned Models by Removing Label Bias in Foundation Models
Figure 2 for Generalized Logit Adjustment: Calibrating Fine-tuned Models by Removing Label Bias in Foundation Models
Figure 3 for Generalized Logit Adjustment: Calibrating Fine-tuned Models by Removing Label Bias in Foundation Models
Figure 4 for Generalized Logit Adjustment: Calibrating Fine-tuned Models by Removing Label Bias in Foundation Models
Viaarxiv icon

Debiased Fine-Tuning for Vision-language Models by Prompt Regularization

Jan 29, 2023
Beier Zhu, Yulei Niu, Saeil Lee, Minhoe Hur, Hanwang Zhang

Figure 1 for Debiased Fine-Tuning for Vision-language Models by Prompt Regularization
Figure 2 for Debiased Fine-Tuning for Vision-language Models by Prompt Regularization
Figure 3 for Debiased Fine-Tuning for Vision-language Models by Prompt Regularization
Figure 4 for Debiased Fine-Tuning for Vision-language Models by Prompt Regularization
Viaarxiv icon

Leveraging Modality-specific Representations for Audio-visual Speech Recognition via Reinforcement Learning

Dec 10, 2022
Chen Chen, Yuchen Hu, Qiang Zhang, Heqing Zou, Beier Zhu, Eng Siong Chng

Figure 1 for Leveraging Modality-specific Representations for Audio-visual Speech Recognition via Reinforcement Learning
Figure 2 for Leveraging Modality-specific Representations for Audio-visual Speech Recognition via Reinforcement Learning
Figure 3 for Leveraging Modality-specific Representations for Audio-visual Speech Recognition via Reinforcement Learning
Figure 4 for Leveraging Modality-specific Representations for Audio-visual Speech Recognition via Reinforcement Learning
Viaarxiv icon

Prompt-aligned Gradient for Prompt Tuning

May 30, 2022
Beier Zhu, Yulei Niu, Yucheng Han, Yue Wu, Hanwang Zhang

Figure 1 for Prompt-aligned Gradient for Prompt Tuning
Figure 2 for Prompt-aligned Gradient for Prompt Tuning
Figure 3 for Prompt-aligned Gradient for Prompt Tuning
Figure 4 for Prompt-aligned Gradient for Prompt Tuning
Viaarxiv icon

Cross-Domain Empirical Risk Minimization for Unbiased Long-tailed Classification

Dec 29, 2021
Beier Zhu, Yulei Niu, Xian-Sheng Hua, Hanwang Zhang

Figure 1 for Cross-Domain Empirical Risk Minimization for Unbiased Long-tailed Classification
Figure 2 for Cross-Domain Empirical Risk Minimization for Unbiased Long-tailed Classification
Figure 3 for Cross-Domain Empirical Risk Minimization for Unbiased Long-tailed Classification
Figure 4 for Cross-Domain Empirical Risk Minimization for Unbiased Long-tailed Classification
Viaarxiv icon

Fast and Accurate: Structure Coherence Component for Face Alignment

Jun 21, 2020
Beier Zhu, Chunze Lin, Quan Wang, Renjie Liao, Chen Qian

Figure 1 for Fast and Accurate: Structure Coherence Component for Face Alignment
Figure 2 for Fast and Accurate: Structure Coherence Component for Face Alignment
Figure 3 for Fast and Accurate: Structure Coherence Component for Face Alignment
Figure 4 for Fast and Accurate: Structure Coherence Component for Face Alignment
Viaarxiv icon