Picture for Umapada Pal

Umapada Pal

Conformal uncertainty quantification to evaluate predictive fairness of foundation AI model for skin lesion classes across patient demographics

Add code
Mar 31, 2025
Viaarxiv icon

A Context-Driven Training-Free Network for Lightweight Scene Text Segmentation and Recognition

Add code
Mar 19, 2025
Viaarxiv icon

d-Sketch: Improving Visual Fidelity of Sketch-to-Image Translation with Pretrained Latent Diffusion Models without Retraining

Add code
Feb 19, 2025
Viaarxiv icon

Exploring Mutual Cross-Modal Attention for Context-Aware Human Affordance Generation

Add code
Feb 19, 2025
Viaarxiv icon

Decorrelation-based Self-Supervised Visual Representation Learning for Writer Identification

Add code
Oct 02, 2024
Figure 1 for Decorrelation-based Self-Supervised Visual Representation Learning for Writer Identification
Figure 2 for Decorrelation-based Self-Supervised Visual Representation Learning for Writer Identification
Figure 3 for Decorrelation-based Self-Supervised Visual Representation Learning for Writer Identification
Figure 4 for Decorrelation-based Self-Supervised Visual Representation Learning for Writer Identification
Viaarxiv icon

FastTextSpotter: A High-Efficiency Transformer for Multilingual Scene Text Spotting

Add code
Aug 27, 2024
Figure 1 for FastTextSpotter: A High-Efficiency Transformer for Multilingual Scene Text Spotting
Figure 2 for FastTextSpotter: A High-Efficiency Transformer for Multilingual Scene Text Spotting
Figure 3 for FastTextSpotter: A High-Efficiency Transformer for Multilingual Scene Text Spotting
Figure 4 for FastTextSpotter: A High-Efficiency Transformer for Multilingual Scene Text Spotting
Viaarxiv icon

Correlation Weighted Prototype-based Self-Supervised One-Shot Segmentation of Medical Images

Add code
Aug 12, 2024
Figure 1 for Correlation Weighted Prototype-based Self-Supervised One-Shot Segmentation of Medical Images
Figure 2 for Correlation Weighted Prototype-based Self-Supervised One-Shot Segmentation of Medical Images
Figure 3 for Correlation Weighted Prototype-based Self-Supervised One-Shot Segmentation of Medical Images
Figure 4 for Correlation Weighted Prototype-based Self-Supervised One-Shot Segmentation of Medical Images
Viaarxiv icon

MDIW-13: a New Multi-Lingual and Multi-Script Database and Benchmark for Script Identification

Add code
May 29, 2024
Viaarxiv icon

SVGCraft: Beyond Single Object Text-to-SVG Synthesis with Comprehensive Canvas Layout

Add code
Mar 30, 2024
Figure 1 for SVGCraft: Beyond Single Object Text-to-SVG Synthesis with Comprehensive Canvas Layout
Figure 2 for SVGCraft: Beyond Single Object Text-to-SVG Synthesis with Comprehensive Canvas Layout
Figure 3 for SVGCraft: Beyond Single Object Text-to-SVG Synthesis with Comprehensive Canvas Layout
Figure 4 for SVGCraft: Beyond Single Object Text-to-SVG Synthesis with Comprehensive Canvas Layout
Viaarxiv icon

GraphKD: Exploring Knowledge Distillation Towards Document Object Detection with Structured Graph Creation

Add code
Feb 20, 2024
Figure 1 for GraphKD: Exploring Knowledge Distillation Towards Document Object Detection with Structured Graph Creation
Figure 2 for GraphKD: Exploring Knowledge Distillation Towards Document Object Detection with Structured Graph Creation
Figure 3 for GraphKD: Exploring Knowledge Distillation Towards Document Object Detection with Structured Graph Creation
Figure 4 for GraphKD: Exploring Knowledge Distillation Towards Document Object Detection with Structured Graph Creation
Viaarxiv icon