Picture for Xiaoyu Wu

Xiaoyu Wu

Exploring Diffusion Models' Corruption Stage in Few-Shot Fine-tuning and Mitigating with Bayesian Neural Networks

Add code
May 30, 2024
Viaarxiv icon

CGI-DM: Digital Copyright Authentication for Diffusion Models via Contrasting Gradient Inversion

Add code
Mar 17, 2024
Figure 1 for CGI-DM: Digital Copyright Authentication for Diffusion Models via Contrasting Gradient Inversion
Figure 2 for CGI-DM: Digital Copyright Authentication for Diffusion Models via Contrasting Gradient Inversion
Figure 3 for CGI-DM: Digital Copyright Authentication for Diffusion Models via Contrasting Gradient Inversion
Figure 4 for CGI-DM: Digital Copyright Authentication for Diffusion Models via Contrasting Gradient Inversion
Viaarxiv icon

Understanding and Improving Adversarial Attacks on Latent Diffusion Model

Add code
Oct 07, 2023
Figure 1 for Understanding and Improving Adversarial Attacks on Latent Diffusion Model
Figure 2 for Understanding and Improving Adversarial Attacks on Latent Diffusion Model
Figure 3 for Understanding and Improving Adversarial Attacks on Latent Diffusion Model
Figure 4 for Understanding and Improving Adversarial Attacks on Latent Diffusion Model
Viaarxiv icon

What Makes Good Open-Vocabulary Detector: A Disassembling Perspective

Add code
Sep 01, 2023
Figure 1 for What Makes Good Open-Vocabulary Detector: A Disassembling Perspective
Figure 2 for What Makes Good Open-Vocabulary Detector: A Disassembling Perspective
Figure 3 for What Makes Good Open-Vocabulary Detector: A Disassembling Perspective
Figure 4 for What Makes Good Open-Vocabulary Detector: A Disassembling Perspective
Viaarxiv icon

Learning Prompt-Enhanced Context Features for Weakly-Supervised Video Anomaly Detection

Add code
Jun 26, 2023
Figure 1 for Learning Prompt-Enhanced Context Features for Weakly-Supervised Video Anomaly Detection
Figure 2 for Learning Prompt-Enhanced Context Features for Weakly-Supervised Video Anomaly Detection
Figure 3 for Learning Prompt-Enhanced Context Features for Weakly-Supervised Video Anomaly Detection
Figure 4 for Learning Prompt-Enhanced Context Features for Weakly-Supervised Video Anomaly Detection
Viaarxiv icon

Mist: Towards Improved Adversarial Examples for Diffusion Models

Add code
May 22, 2023
Figure 1 for Mist: Towards Improved Adversarial Examples for Diffusion Models
Figure 2 for Mist: Towards Improved Adversarial Examples for Diffusion Models
Figure 3 for Mist: Towards Improved Adversarial Examples for Diffusion Models
Figure 4 for Mist: Towards Improved Adversarial Examples for Diffusion Models
Viaarxiv icon

Adversarial Example Does Good: Preventing Painting Imitation from Diffusion Models via Adversarial Examples

Add code
Feb 09, 2023
Figure 1 for Adversarial Example Does Good: Preventing Painting Imitation from Diffusion Models via Adversarial Examples
Figure 2 for Adversarial Example Does Good: Preventing Painting Imitation from Diffusion Models via Adversarial Examples
Figure 3 for Adversarial Example Does Good: Preventing Painting Imitation from Diffusion Models via Adversarial Examples
Figure 4 for Adversarial Example Does Good: Preventing Painting Imitation from Diffusion Models via Adversarial Examples
Viaarxiv icon

Temporal and Contextual Transformer for Multi-Camera Editing of TV Shows

Add code
Oct 17, 2022
Figure 1 for Temporal and Contextual Transformer for Multi-Camera Editing of TV Shows
Figure 2 for Temporal and Contextual Transformer for Multi-Camera Editing of TV Shows
Figure 3 for Temporal and Contextual Transformer for Multi-Camera Editing of TV Shows
Figure 4 for Temporal and Contextual Transformer for Multi-Camera Editing of TV Shows
Viaarxiv icon

Locality-aware Attention Network with Discriminative Dynamics Learning for Weakly Supervised Anomaly Detection

Add code
Aug 11, 2022
Figure 1 for Locality-aware Attention Network with Discriminative Dynamics Learning for Weakly Supervised Anomaly Detection
Figure 2 for Locality-aware Attention Network with Discriminative Dynamics Learning for Weakly Supervised Anomaly Detection
Figure 3 for Locality-aware Attention Network with Discriminative Dynamics Learning for Weakly Supervised Anomaly Detection
Figure 4 for Locality-aware Attention Network with Discriminative Dynamics Learning for Weakly Supervised Anomaly Detection
Viaarxiv icon

Zero and R2D2: A Large-scale Chinese Cross-modal Benchmark and A Vision-Language Framework

Add code
May 08, 2022
Figure 1 for Zero and R2D2: A Large-scale Chinese Cross-modal Benchmark and A Vision-Language Framework
Figure 2 for Zero and R2D2: A Large-scale Chinese Cross-modal Benchmark and A Vision-Language Framework
Figure 3 for Zero and R2D2: A Large-scale Chinese Cross-modal Benchmark and A Vision-Language Framework
Figure 4 for Zero and R2D2: A Large-scale Chinese Cross-modal Benchmark and A Vision-Language Framework
Viaarxiv icon