Picture for Changqing Zhang

Changqing Zhang

Common and Rare Fundus Diseases Identification Using Vision-Language Foundation Model with Knowledge of Over 400 Diseases

Add code
Jun 13, 2024
Viaarxiv icon

Predictive Dynamic Fusion

Add code
Jun 07, 2024
Figure 1 for Predictive Dynamic Fusion
Figure 2 for Predictive Dynamic Fusion
Figure 3 for Predictive Dynamic Fusion
Figure 4 for Predictive Dynamic Fusion
Viaarxiv icon

Confidence-aware multi-modality learning for eye disease screening

Add code
May 28, 2024
Viaarxiv icon

Multimodal Fusion on Low-quality Data: A Comprehensive Survey

Add code
Apr 27, 2024
Figure 1 for Multimodal Fusion on Low-quality Data: A Comprehensive Survey
Figure 2 for Multimodal Fusion on Low-quality Data: A Comprehensive Survey
Figure 3 for Multimodal Fusion on Low-quality Data: A Comprehensive Survey
Figure 4 for Multimodal Fusion on Low-quality Data: A Comprehensive Survey
Viaarxiv icon

Invariant Test-Time Adaptation for Vision-Language Model Generalization

Add code
Mar 01, 2024
Figure 1 for Invariant Test-Time Adaptation for Vision-Language Model Generalization
Figure 2 for Invariant Test-Time Adaptation for Vision-Language Model Generalization
Figure 3 for Invariant Test-Time Adaptation for Vision-Language Model Generalization
Figure 4 for Invariant Test-Time Adaptation for Vision-Language Model Generalization
Viaarxiv icon

Selective Learning: Towards Robust Calibration with Dynamic Regularization

Add code
Feb 13, 2024
Figure 1 for Selective Learning: Towards Robust Calibration with Dynamic Regularization
Figure 2 for Selective Learning: Towards Robust Calibration with Dynamic Regularization
Figure 3 for Selective Learning: Towards Robust Calibration with Dynamic Regularization
Figure 4 for Selective Learning: Towards Robust Calibration with Dynamic Regularization
Viaarxiv icon

Skip : A Simple Method to Reduce Hallucination in Large Vision-Language Models

Add code
Feb 12, 2024
Figure 1 for Skip : A Simple Method to Reduce Hallucination in Large Vision-Language Models
Figure 2 for Skip : A Simple Method to Reduce Hallucination in Large Vision-Language Models
Figure 3 for Skip : A Simple Method to Reduce Hallucination in Large Vision-Language Models
Figure 4 for Skip : A Simple Method to Reduce Hallucination in Large Vision-Language Models
Viaarxiv icon

ID-like Prompt Learning for Few-Shot Out-of-Distribution Detection

Add code
Nov 28, 2023
Figure 1 for ID-like Prompt Learning for Few-Shot Out-of-Distribution Detection
Figure 2 for ID-like Prompt Learning for Few-Shot Out-of-Distribution Detection
Figure 3 for ID-like Prompt Learning for Few-Shot Out-of-Distribution Detection
Figure 4 for ID-like Prompt Learning for Few-Shot Out-of-Distribution Detection
Viaarxiv icon

Adapting Large Language Models for Content Moderation: Pitfalls in Data Engineering and Supervised Fine-tuning

Add code
Oct 05, 2023
Figure 1 for Adapting Large Language Models for Content Moderation: Pitfalls in Data Engineering and Supervised Fine-tuning
Figure 2 for Adapting Large Language Models for Content Moderation: Pitfalls in Data Engineering and Supervised Fine-tuning
Figure 3 for Adapting Large Language Models for Content Moderation: Pitfalls in Data Engineering and Supervised Fine-tuning
Figure 4 for Adapting Large Language Models for Content Moderation: Pitfalls in Data Engineering and Supervised Fine-tuning
Viaarxiv icon

Semantic Equivariant Mixup

Add code
Aug 12, 2023
Viaarxiv icon