Picture for Sanghyun Jo

Sanghyun Jo

COIN: Confidence Score-Guided Distillation for Annotation-Free Cell Segmentation

Add code
Mar 17, 2025
Viaarxiv icon

DiffEGG: Diffusion-Driven Edge Generation as a Pixel-Annotation-Free Alternative for Instance Annotation

Add code
Mar 11, 2025
Viaarxiv icon

TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias

Add code
Mar 30, 2024
Figure 1 for TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias
Figure 2 for TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias
Figure 3 for TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias
Figure 4 for TTD: Text-Tag Self-Distillation Enhancing Image-Text Alignment in CLIP to Alleviate Single Tag Bias
Viaarxiv icon

DHR: Dual Features-Driven Hierarchical Rebalancing in Inter- and Intra-Class Regions for Weakly-Supervised Semantic Segmentation

Add code
Mar 30, 2024
Viaarxiv icon

MARS: Model-agnostic Biased Object Removal without Additional Supervision for Weakly-Supervised Semantic Segmentation

Add code
Apr 19, 2023
Viaarxiv icon

Puzzle-CAM: Improved localization via matching partial and full features

Add code
Feb 02, 2021
Figure 1 for Puzzle-CAM: Improved localization via matching partial and full features
Figure 2 for Puzzle-CAM: Improved localization via matching partial and full features
Figure 3 for Puzzle-CAM: Improved localization via matching partial and full features
Figure 4 for Puzzle-CAM: Improved localization via matching partial and full features
Viaarxiv icon