Picture for Yizeng Han

Yizeng Han

DyFADet: Dynamic Feature Aggregation for Temporal Action Detection

Add code
Jul 03, 2024
Viaarxiv icon

Demystify Mamba in Vision: A Linear Attention Perspective

Add code
May 26, 2024
Figure 1 for Demystify Mamba in Vision: A Linear Attention Perspective
Figure 2 for Demystify Mamba in Vision: A Linear Attention Perspective
Figure 3 for Demystify Mamba in Vision: A Linear Attention Perspective
Figure 4 for Demystify Mamba in Vision: A Linear Attention Perspective
Viaarxiv icon

EfficientTrain++: Generalized Curriculum Learning for Efficient Visual Backbone Training

Add code
May 14, 2024
Figure 1 for EfficientTrain++: Generalized Curriculum Learning for Efficient Visual Backbone Training
Figure 2 for EfficientTrain++: Generalized Curriculum Learning for Efficient Visual Backbone Training
Figure 3 for EfficientTrain++: Generalized Curriculum Learning for Efficient Visual Backbone Training
Figure 4 for EfficientTrain++: Generalized Curriculum Learning for Efficient Visual Backbone Training
Viaarxiv icon

GRA: Detecting Oriented Objects through Group-wise Rotating and Attention

Add code
Mar 19, 2024
Figure 1 for GRA: Detecting Oriented Objects through Group-wise Rotating and Attention
Figure 2 for GRA: Detecting Oriented Objects through Group-wise Rotating and Attention
Figure 3 for GRA: Detecting Oriented Objects through Group-wise Rotating and Attention
Figure 4 for GRA: Detecting Oriented Objects through Group-wise Rotating and Attention
Viaarxiv icon

Dynamic Tuning Towards Parameter and Inference Efficiency for ViT Adaptation

Add code
Mar 18, 2024
Figure 1 for Dynamic Tuning Towards Parameter and Inference Efficiency for ViT Adaptation
Figure 2 for Dynamic Tuning Towards Parameter and Inference Efficiency for ViT Adaptation
Figure 3 for Dynamic Tuning Towards Parameter and Inference Efficiency for ViT Adaptation
Figure 4 for Dynamic Tuning Towards Parameter and Inference Efficiency for ViT Adaptation
Viaarxiv icon

SimPro: A Simple Probabilistic Framework Towards Realistic Long-Tailed Semi-Supervised Learning

Add code
Feb 21, 2024
Figure 1 for SimPro: A Simple Probabilistic Framework Towards Realistic Long-Tailed Semi-Supervised Learning
Figure 2 for SimPro: A Simple Probabilistic Framework Towards Realistic Long-Tailed Semi-Supervised Learning
Figure 3 for SimPro: A Simple Probabilistic Framework Towards Realistic Long-Tailed Semi-Supervised Learning
Figure 4 for SimPro: A Simple Probabilistic Framework Towards Realistic Long-Tailed Semi-Supervised Learning
Viaarxiv icon

Agent Attention: On the Integration of Softmax and Linear Attention

Add code
Dec 22, 2023
Figure 1 for Agent Attention: On the Integration of Softmax and Linear Attention
Figure 2 for Agent Attention: On the Integration of Softmax and Linear Attention
Figure 3 for Agent Attention: On the Integration of Softmax and Linear Attention
Figure 4 for Agent Attention: On the Integration of Softmax and Linear Attention
Viaarxiv icon

Mask Grounding for Referring Image Segmentation

Add code
Dec 19, 2023
Viaarxiv icon

GSVA: Generalized Segmentation via Multimodal Large Language Models

Add code
Dec 15, 2023
Figure 1 for GSVA: Generalized Segmentation via Multimodal Large Language Models
Figure 2 for GSVA: Generalized Segmentation via Multimodal Large Language Models
Figure 3 for GSVA: Generalized Segmentation via Multimodal Large Language Models
Figure 4 for GSVA: Generalized Segmentation via Multimodal Large Language Models
Viaarxiv icon

Latency-aware Unified Dynamic Networks for Efficient Image Recognition

Add code
Sep 02, 2023
Figure 1 for Latency-aware Unified Dynamic Networks for Efficient Image Recognition
Figure 2 for Latency-aware Unified Dynamic Networks for Efficient Image Recognition
Figure 3 for Latency-aware Unified Dynamic Networks for Efficient Image Recognition
Figure 4 for Latency-aware Unified Dynamic Networks for Efficient Image Recognition
Viaarxiv icon