Picture for Yibing Liu

Yibing Liu

Gradient-Congruity Guided Federated Sparse Training

Add code
May 02, 2024
Viaarxiv icon

Neuron Activation Coverage: Rethinking Out-of-distribution Detection and Generalization

Add code
Jun 05, 2023
Viaarxiv icon

M3FAS: An Accurate and Robust MultiModal Mobile Face Anti-Spoofing System

Add code
Feb 03, 2023
Viaarxiv icon

Generalization Beyond Feature Alignment: Concept Activation-Guided Contrastive Learning

Add code
Nov 13, 2022
Viaarxiv icon

A Unified End-to-End Retriever-Reader Framework for Knowledge-based VQA

Add code
Jun 30, 2022
Figure 1 for A Unified End-to-End Retriever-Reader Framework for Knowledge-based VQA
Figure 2 for A Unified End-to-End Retriever-Reader Framework for Knowledge-based VQA
Figure 3 for A Unified End-to-End Retriever-Reader Framework for Knowledge-based VQA
Figure 4 for A Unified End-to-End Retriever-Reader Framework for Knowledge-based VQA
Viaarxiv icon

Rethinking Attention-Model Explainability through Faithfulness Violation Test

Add code
Jan 28, 2022
Figure 1 for Rethinking Attention-Model Explainability through Faithfulness Violation Test
Figure 2 for Rethinking Attention-Model Explainability through Faithfulness Violation Test
Figure 3 for Rethinking Attention-Model Explainability through Faithfulness Violation Test
Figure 4 for Rethinking Attention-Model Explainability through Faithfulness Violation Test
Viaarxiv icon

Answer Questions with Right Image Regions: A Visual Attention Regularization Approach

Add code
Feb 03, 2021
Figure 1 for Answer Questions with Right Image Regions: A Visual Attention Regularization Approach
Figure 2 for Answer Questions with Right Image Regions: A Visual Attention Regularization Approach
Figure 3 for Answer Questions with Right Image Regions: A Visual Attention Regularization Approach
Figure 4 for Answer Questions with Right Image Regions: A Visual Attention Regularization Approach
Viaarxiv icon

Distilling Knowledge from Pre-trained Language Models via Text Smoothing

Add code
May 08, 2020
Figure 1 for Distilling Knowledge from Pre-trained Language Models via Text Smoothing
Figure 2 for Distilling Knowledge from Pre-trained Language Models via Text Smoothing
Figure 3 for Distilling Knowledge from Pre-trained Language Models via Text Smoothing
Figure 4 for Distilling Knowledge from Pre-trained Language Models via Text Smoothing
Viaarxiv icon

Quantifying and Alleviating the Language Prior Problem in Visual Question Answering

Add code
May 13, 2019
Figure 1 for Quantifying and Alleviating the Language Prior Problem in Visual Question Answering
Figure 2 for Quantifying and Alleviating the Language Prior Problem in Visual Question Answering
Figure 3 for Quantifying and Alleviating the Language Prior Problem in Visual Question Answering
Figure 4 for Quantifying and Alleviating the Language Prior Problem in Visual Question Answering
Viaarxiv icon