Picture for Lei Qi

Lei Qi

KAnoCLIP: Zero-Shot Anomaly Detection through Knowledge-Driven Prompt Learning and Enhanced Cross-Modal Integration

Add code
Jan 07, 2025
Viaarxiv icon

BatStyler: Advancing Multi-category Style Generation for Source-free Domain Generalization

Add code
Jan 02, 2025
Viaarxiv icon

Text and Image Are Mutually Beneficial: Enhancing Training-Free Few-Shot Classification with CLIP

Add code
Dec 16, 2024
Viaarxiv icon

START: A Generalized State Space Model with Saliency-Driven Token-Aware Transformation

Add code
Oct 21, 2024
Figure 1 for START: A Generalized State Space Model with Saliency-Driven Token-Aware Transformation
Figure 2 for START: A Generalized State Space Model with Saliency-Driven Token-Aware Transformation
Figure 3 for START: A Generalized State Space Model with Saliency-Driven Token-Aware Transformation
Figure 4 for START: A Generalized State Space Model with Saliency-Driven Token-Aware Transformation
Viaarxiv icon

Dual-Teacher Ensemble Models with Double-Copy-Paste for 3D Semi-Supervised Medical Image Segmentation

Add code
Oct 15, 2024
Figure 1 for Dual-Teacher Ensemble Models with Double-Copy-Paste for 3D Semi-Supervised Medical Image Segmentation
Figure 2 for Dual-Teacher Ensemble Models with Double-Copy-Paste for 3D Semi-Supervised Medical Image Segmentation
Figure 3 for Dual-Teacher Ensemble Models with Double-Copy-Paste for 3D Semi-Supervised Medical Image Segmentation
Figure 4 for Dual-Teacher Ensemble Models with Double-Copy-Paste for 3D Semi-Supervised Medical Image Segmentation
Viaarxiv icon

CLIP-DFGS: A Hard Sample Mining Method for CLIP in Generalizable Person Re-Identification

Add code
Oct 15, 2024
Viaarxiv icon

PC$^2$: Pseudo-Classification Based Pseudo-Captioning for Noisy Correspondence Learning in Cross-Modal Retrieval

Add code
Aug 02, 2024
Figure 1 for PC$^2$: Pseudo-Classification Based Pseudo-Captioning for Noisy Correspondence Learning in Cross-Modal Retrieval
Figure 2 for PC$^2$: Pseudo-Classification Based Pseudo-Captioning for Noisy Correspondence Learning in Cross-Modal Retrieval
Figure 3 for PC$^2$: Pseudo-Classification Based Pseudo-Captioning for Noisy Correspondence Learning in Cross-Modal Retrieval
Figure 4 for PC$^2$: Pseudo-Classification Based Pseudo-Captioning for Noisy Correspondence Learning in Cross-Modal Retrieval
Viaarxiv icon

ChipExpert: The Open-Source Integrated-Circuit-Design-Specific Large Language Model

Add code
Jul 26, 2024
Viaarxiv icon

Learn to Preserve and Diversify: Parameter-Efficient Group with Orthogonal Regularization for Domain Generalization

Add code
Jul 21, 2024
Figure 1 for Learn to Preserve and Diversify: Parameter-Efficient Group with Orthogonal Regularization for Domain Generalization
Figure 2 for Learn to Preserve and Diversify: Parameter-Efficient Group with Orthogonal Regularization for Domain Generalization
Figure 3 for Learn to Preserve and Diversify: Parameter-Efficient Group with Orthogonal Regularization for Domain Generalization
Figure 4 for Learn to Preserve and Diversify: Parameter-Efficient Group with Orthogonal Regularization for Domain Generalization
Viaarxiv icon

The Devil is in the Statistics: Mitigating and Exploiting Statistics Difference for Generalizable Semi-supervised Medical Image Segmentation

Add code
Jul 16, 2024
Figure 1 for The Devil is in the Statistics: Mitigating and Exploiting Statistics Difference for Generalizable Semi-supervised Medical Image Segmentation
Figure 2 for The Devil is in the Statistics: Mitigating and Exploiting Statistics Difference for Generalizable Semi-supervised Medical Image Segmentation
Figure 3 for The Devil is in the Statistics: Mitigating and Exploiting Statistics Difference for Generalizable Semi-supervised Medical Image Segmentation
Figure 4 for The Devil is in the Statistics: Mitigating and Exploiting Statistics Difference for Generalizable Semi-supervised Medical Image Segmentation
Viaarxiv icon