Picture for Kwanghoon Sohn

Kwanghoon Sohn

Rethinking Open-World Semi-Supervised Learning: Distribution Mismatch and Inductive Inference

May 31, 2024
Viaarxiv icon

Diffusion-driven GAN Inversion for Multi-Modal Face Image Generation

Add code
May 07, 2024
Viaarxiv icon

Bridging Vision and Language Spaces with Assignment Prediction

Add code
Apr 15, 2024
Figure 1 for Bridging Vision and Language Spaces with Assignment Prediction
Figure 2 for Bridging Vision and Language Spaces with Assignment Prediction
Figure 3 for Bridging Vision and Language Spaces with Assignment Prediction
Figure 4 for Bridging Vision and Language Spaces with Assignment Prediction
Viaarxiv icon

Improving Visual Recognition with Hyperbolical Visual Hierarchy Mapping

Add code
Apr 01, 2024
Viaarxiv icon

Layer-wise Auto-Weighting for Non-Stationary Test-Time Adaptation

Add code
Nov 26, 2023
Figure 1 for Layer-wise Auto-Weighting for Non-Stationary Test-Time Adaptation
Figure 2 for Layer-wise Auto-Weighting for Non-Stationary Test-Time Adaptation
Figure 3 for Layer-wise Auto-Weighting for Non-Stationary Test-Time Adaptation
Figure 4 for Layer-wise Auto-Weighting for Non-Stationary Test-Time Adaptation
Viaarxiv icon

Knowing Where to Focus: Event-aware Transformer for Video Grounding

Add code
Aug 14, 2023
Figure 1 for Knowing Where to Focus: Event-aware Transformer for Video Grounding
Figure 2 for Knowing Where to Focus: Event-aware Transformer for Video Grounding
Figure 3 for Knowing Where to Focus: Event-aware Transformer for Video Grounding
Figure 4 for Knowing Where to Focus: Event-aware Transformer for Video Grounding
Viaarxiv icon

Semantic-aware Network for Aerial-to-Ground Image Synthesis

Add code
Aug 14, 2023
Figure 1 for Semantic-aware Network for Aerial-to-Ground Image Synthesis
Figure 2 for Semantic-aware Network for Aerial-to-Ground Image Synthesis
Figure 3 for Semantic-aware Network for Aerial-to-Ground Image Synthesis
Figure 4 for Semantic-aware Network for Aerial-to-Ground Image Synthesis
Viaarxiv icon

Hierarchical Visual Primitive Experts for Compositional Zero-Shot Learning

Add code
Aug 08, 2023
Figure 1 for Hierarchical Visual Primitive Experts for Compositional Zero-Shot Learning
Figure 2 for Hierarchical Visual Primitive Experts for Compositional Zero-Shot Learning
Figure 3 for Hierarchical Visual Primitive Experts for Compositional Zero-Shot Learning
Figure 4 for Hierarchical Visual Primitive Experts for Compositional Zero-Shot Learning
Viaarxiv icon

PartMix: Regularization Strategy to Learn Part Discovery for Visible-Infrared Person Re-identification

Apr 04, 2023
Figure 1 for PartMix: Regularization Strategy to Learn Part Discovery for Visible-Infrared Person Re-identification
Figure 2 for PartMix: Regularization Strategy to Learn Part Discovery for Visible-Infrared Person Re-identification
Figure 3 for PartMix: Regularization Strategy to Learn Part Discovery for Visible-Infrared Person Re-identification
Figure 4 for PartMix: Regularization Strategy to Learn Part Discovery for Visible-Infrared Person Re-identification
Viaarxiv icon

Probabilistic Prompt Learning for Dense Prediction

Apr 03, 2023
Figure 1 for Probabilistic Prompt Learning for Dense Prediction
Figure 2 for Probabilistic Prompt Learning for Dense Prediction
Figure 3 for Probabilistic Prompt Learning for Dense Prediction
Figure 4 for Probabilistic Prompt Learning for Dense Prediction
Viaarxiv icon