Picture for Zijun Long

Zijun Long

Understanding and Mitigating Human-Labelling Errors in Supervised Contrastive Learning

Add code
Mar 10, 2024
Figure 1 for Understanding and Mitigating Human-Labelling Errors in Supervised Contrastive Learning
Figure 2 for Understanding and Mitigating Human-Labelling Errors in Supervised Contrastive Learning
Figure 3 for Understanding and Mitigating Human-Labelling Errors in Supervised Contrastive Learning
Figure 4 for Understanding and Mitigating Human-Labelling Errors in Supervised Contrastive Learning
Viaarxiv icon

Text2Pic Swift: Enhancing Long-Text to Image Retrieval for Large-Scale Libraries

Add code
Feb 28, 2024
Figure 1 for Text2Pic Swift: Enhancing Long-Text to Image Retrieval for Large-Scale Libraries
Figure 2 for Text2Pic Swift: Enhancing Long-Text to Image Retrieval for Large-Scale Libraries
Figure 3 for Text2Pic Swift: Enhancing Long-Text to Image Retrieval for Large-Scale Libraries
Figure 4 for Text2Pic Swift: Enhancing Long-Text to Image Retrieval for Large-Scale Libraries
Viaarxiv icon

CLCE: An Approach to Refining Cross-Entropy and Contrastive Learning for Optimized Learning Fusion

Add code
Feb 22, 2024
Figure 1 for CLCE: An Approach to Refining Cross-Entropy and Contrastive Learning for Optimized Learning Fusion
Figure 2 for CLCE: An Approach to Refining Cross-Entropy and Contrastive Learning for Optimized Learning Fusion
Figure 3 for CLCE: An Approach to Refining Cross-Entropy and Contrastive Learning for Optimized Learning Fusion
Figure 4 for CLCE: An Approach to Refining Cross-Entropy and Contrastive Learning for Optimized Learning Fusion
Viaarxiv icon

CrisisViT: A Robust Vision Transformer for Crisis Image Classification

Add code
Jan 05, 2024
Viaarxiv icon

Elucidating and Overcoming the Challenges of Label Noise in Supervised Contrastive Learning

Add code
Nov 25, 2023
Viaarxiv icon

Large Multi-modal Encoders for Recommendation

Add code
Nov 03, 2023
Viaarxiv icon

RoboLLM: Robotic Vision Tasks Grounded on Multimodal Large Language Models

Add code
Oct 16, 2023
Viaarxiv icon

MultiWay-Adapater: Adapting large-scale multi-modal models for scalable image-text retrieval

Add code
Sep 12, 2023
Viaarxiv icon

When hard negative sampling meets supervised contrastive learning

Add code
Aug 28, 2023
Figure 1 for When hard negative sampling meets supervised contrastive learning
Figure 2 for When hard negative sampling meets supervised contrastive learning
Figure 3 for When hard negative sampling meets supervised contrastive learning
Figure 4 for When hard negative sampling meets supervised contrastive learning
Viaarxiv icon

LaCViT: A Label-aware Contrastive Training Framework for Vision Transformers

Add code
Mar 31, 2023
Figure 1 for LaCViT: A Label-aware Contrastive Training Framework for Vision Transformers
Figure 2 for LaCViT: A Label-aware Contrastive Training Framework for Vision Transformers
Figure 3 for LaCViT: A Label-aware Contrastive Training Framework for Vision Transformers
Figure 4 for LaCViT: A Label-aware Contrastive Training Framework for Vision Transformers
Viaarxiv icon