Picture for Hironobu Fujiyoshi

Hironobu Fujiyoshi

DeBiFormer: Vision Transformer with Deformable Agent Bi-level Routing Attention

Add code
Oct 11, 2024
Figure 1 for DeBiFormer: Vision Transformer with Deformable Agent Bi-level Routing Attention
Figure 2 for DeBiFormer: Vision Transformer with Deformable Agent Bi-level Routing Attention
Figure 3 for DeBiFormer: Vision Transformer with Deformable Agent Bi-level Routing Attention
Figure 4 for DeBiFormer: Vision Transformer with Deformable Agent Bi-level Routing Attention
Viaarxiv icon

Nearest Neighbor Future Captioning: Generating Descriptions for Possible Collisions in Object Placement Tasks

Add code
Jul 18, 2024
Figure 1 for Nearest Neighbor Future Captioning: Generating Descriptions for Possible Collisions in Object Placement Tasks
Figure 2 for Nearest Neighbor Future Captioning: Generating Descriptions for Possible Collisions in Object Placement Tasks
Figure 3 for Nearest Neighbor Future Captioning: Generating Descriptions for Possible Collisions in Object Placement Tasks
Figure 4 for Nearest Neighbor Future Captioning: Generating Descriptions for Possible Collisions in Object Placement Tasks
Viaarxiv icon

Layer-Wise Relevance Propagation with Conservation Property for ResNet

Add code
Jul 12, 2024
Figure 1 for Layer-Wise Relevance Propagation with Conservation Property for ResNet
Figure 2 for Layer-Wise Relevance Propagation with Conservation Property for ResNet
Figure 3 for Layer-Wise Relevance Propagation with Conservation Property for ResNet
Figure 4 for Layer-Wise Relevance Propagation with Conservation Property for ResNet
Viaarxiv icon

Action Q-Transformer: Visual Explanation in Deep Reinforcement Learning with Encoder-Decoder Model using Action Query

Add code
Jun 24, 2023
Viaarxiv icon

Learning from AI: An Interactive Learning Method Using a DNN Model Incorporating Expert Knowledge as a Teacher

Add code
Jun 04, 2023
Viaarxiv icon

Masking and Mixing Adversarial Training

Add code
Feb 16, 2023
Figure 1 for Masking and Mixing Adversarial Training
Figure 2 for Masking and Mixing Adversarial Training
Figure 3 for Masking and Mixing Adversarial Training
Figure 4 for Masking and Mixing Adversarial Training
Viaarxiv icon

Data Augmentation by Selecting Mixed Classes Considering Distance Between Classes

Add code
Sep 12, 2022
Figure 1 for Data Augmentation by Selecting Mixed Classes Considering Distance Between Classes
Figure 2 for Data Augmentation by Selecting Mixed Classes Considering Distance Between Classes
Figure 3 for Data Augmentation by Selecting Mixed Classes Considering Distance Between Classes
Figure 4 for Data Augmentation by Selecting Mixed Classes Considering Distance Between Classes
Viaarxiv icon

Visual Explanation of Deep Q-Network for Robot Navigation by Fine-tuning Attention Branch

Add code
Aug 18, 2022
Figure 1 for Visual Explanation of Deep Q-Network for Robot Navigation by Fine-tuning Attention Branch
Figure 2 for Visual Explanation of Deep Q-Network for Robot Navigation by Fine-tuning Attention Branch
Figure 3 for Visual Explanation of Deep Q-Network for Robot Navigation by Fine-tuning Attention Branch
Figure 4 for Visual Explanation of Deep Q-Network for Robot Navigation by Fine-tuning Attention Branch
Viaarxiv icon

Object-ABN: Learning to Generate Sharp Attention Maps for Action Recognition

Add code
Jul 27, 2022
Figure 1 for Object-ABN: Learning to Generate Sharp Attention Maps for Action Recognition
Figure 2 for Object-ABN: Learning to Generate Sharp Attention Maps for Action Recognition
Figure 3 for Object-ABN: Learning to Generate Sharp Attention Maps for Action Recognition
Figure 4 for Object-ABN: Learning to Generate Sharp Attention Maps for Action Recognition
Viaarxiv icon

ST-ABN: Visual Explanation Taking into Account Spatio-temporal Information for Video Recognition

Add code
Oct 29, 2021
Figure 1 for ST-ABN: Visual Explanation Taking into Account Spatio-temporal Information for Video Recognition
Figure 2 for ST-ABN: Visual Explanation Taking into Account Spatio-temporal Information for Video Recognition
Figure 3 for ST-ABN: Visual Explanation Taking into Account Spatio-temporal Information for Video Recognition
Figure 4 for ST-ABN: Visual Explanation Taking into Account Spatio-temporal Information for Video Recognition
Viaarxiv icon