69 citations · 243 across the 31 of their papers we have counts for
24 papers · 1 filter
DeepfakeBench: A Comprehensive Benchmark of Deepfake Detection
Zhiyuan Yan, Yong Zhang, Xinhang Yuan +2
A critical yet frequently overlooked challenge in the field of deepfake detection is the lack of a standardized, unified, comprehensive benchmark. This issue leads to unfair perfor…
Versatile Backdoor Attack with Visible, Semantic, Sample-Specific, and Compatible Triggers
Ruotong Wang, Hongrui Chen, Zihao Zhu +2
Deep neural networks (DNNs) can be manipulated to exhibit specific behaviors when exposed to specific trigger patterns, without affecting their performance on benign samples, dubbe…
UCF: Uncovering Common Features for Generalizable Deepfake Detection
Zhiyuan Yan, Yong Zhang, Yanbo Fan +1
Deepfake detection remains a challenging task due to the difficulty of generalizing to new types of forgeries. This problem primarily stems from the overfitting of existing detecti…
3D GAN Inversion with Facial Symmetry Prior
Fei Yin, Yong Zhang, Xuan Wang +8
Recently, a surge of high-quality 3D-aware GANs have been proposed, which leverage the generative power of neural rendering. It is natural to associate 3D GANs with GAN inversion m…
Fine-Grained Face Swapping via Regional GAN Inversion
Zhian Liu, Maomao Li, Yong Zhang +4
We present a novel paradigm for high-fidelity face swapping that faithfully preserves the desired subtle geometry and texture details. We rethink face swapping from the perspective…
Boosting the Transferability of Adversarial Attacks with Reverse Adversarial Perturbation
Zeyu Qin, Yanbo Fan, Yi Liu +4
Deep neural networks (DNNs) have been shown to be vulnerable to adversarial examples, which can produce erroneous predictions by injecting imperceptible perturbations. In this work…
Towards Real-World Video Deblurring by Exploring Blur Formation Process
Mingdeng Cao, Zhihang Zhong, Yanbo Fan +5
This paper aims at exploring how to synthesize close-to-real blurs that existing video deblurring models trained on them can generalize well to real-world blurry videos. In recent…
Prior-Guided Adversarial Initialization for Fast Adversarial Training
Xiaojun Jia, Yong Zhang, Xingxing Wei +4
Fast adversarial training (FAT) effectively improves the efficiency of standard adversarial training (SAT). However, initial FAT encounters catastrophic overfitting, i.e.,the robus…
VDTR: Video Deblurring with Transformer
Mingdeng Cao, Yanbo Fan, Yong Zhang +2
Video deblurring is still an unsolved problem due to the challenging spatio-temporal modeling process. While existing convolutional neural network-based methods show a limited capa…
StyleHEAT: One-Shot High-Resolution Editable Talking Face Generation via Pre-trained StyleGAN
Fei Yin, Yong Zhang, Xiaodong Cun +7
One-shot talking face generation aims at synthesizing a high-quality talking face video from an arbitrary portrait image, driven by a video or an audio segment. One challenging qua…
LAS-AT: Adversarial Training with Learnable Attack Strategy
Xiaojun Jia, Yong Zhang, Baoyuan Wu +3
Adversarial training (AT) is always formulated as a minimax problem, of which the performance depends on the inner optimization that involves the generation of adversarial examples…
FENeRF: Face Editing in Neural Radiance Fields
Jingxiang Sun, Xuan Wang, Yong Zhang +4
Previous portrait image generation methods roughly fall into two categories: 2D GANs and 3D-aware GANs. 2D GANs can generate high fidelity portraits but with low view consistency.…
Repaint: Improving the Generalization of Down-Stream Visual Tasks by Generating Multiple Instances of Training Examples
Amin Banitalebi-Dehkordi, Yong Zhang
Convolutional Neural Networks (CNNs) for visual tasks are believed to learn both the low-level textures and high-level object attributes, throughout the network depth. This paper f…
EBJR: Energy-Based Joint Reasoning for Adaptive Inference
Mohammad Akbari, Amin Banitalebi-Dehkordi, Yong Zhang
State-of-the-art deep learning models have achieved significant performance levels on various benchmarks. However, the excellent performance comes at a cost of inefficient computat…
Boosting Fast Adversarial Training with Learnable Adversarial Initialization
Xiaojun Jia, Yong Zhang, Baoyuan Wu +2
Adversarial training (AT) has been demonstrated to be effective in improving model robustness by leveraging adversarial examples for training. However, most AT methods are in face…
Robust Physical-World Attacks on Face Recognition
Xin Zheng, Yanbo Fan, Baoyuan Wu +3
Face recognition has been greatly facilitated by the development of deep neural networks (DNNs) and has been widely applied to many safety-critical applications. However, recent st…
High-Fidelity GAN Inversion for Image Attribute Editing
Tengfei Wang, Yong Zhang, Yanbo Fan +2
We present a novel high-fidelity generative adversarial network (GAN) inversion framework that enables attribute editing with image-specific details well-preserved (e.g., backgroun…
DAE-GAN: Dynamic Aspect-aware GAN for Text-to-Image Synthesis
Shulan Ruan, Yong Zhang, Kun Zhang +4
Text-to-image synthesis refers to generating an image from a given text description, the key goal of which lies in photo realism and semantic consistency. Previous methods usually…
An Effective and Robust Detector for Logo Detection
Xiaojun Jia, Huanqian Yan, Yonglin Wu +3
In recent years, intellectual property (IP), which represents literary, inventions, artistic works, etc, gradually attract more and more people's attention. Particularly, with the…
SimROD: A Simple Adaptation Method for Robust Object Detection
Rindra Ramamonjison, Amin Banitalebi-Dehkordi, Xinyu Kang +2
This paper presents a Simple and effective unsupervised adaptation method for Robust Object Detection (SimROD). To overcome the challenging issues of domain shift and pseudo-label…
Probabilistic Modeling of Semantic Ambiguity for Scene Graph Generation
Gengcong Yang, Jingyi Zhang, Yong Zhang +2
To generate "accurate" scene graphs, almost all existing methods predict pairwise relationships in a deterministic manner. However, we argue that visual relationships are often sem…
Dual ResGCN for Balanced Scene GraphGeneration
Jingyi Zhang, Yong Zhang, Baoyuan Wu +3
Visual scene graph generation is a challenging task. Previous works have achieved great progress, but most of them do not explicitly consider the class imbalance issue in scene gra…
Effective and Robust Detection of Adversarial Examples via Benford-Fourier Coefficients
Chengcheng Ma, Baoyuan Wu, Shibiao Xu +4
Adversarial examples have been well known as a serious threat to deep neural networks (DNNs). In this work, we study the detection of adversarial examples, based on the assumption…
Controllable Descendant Face Synthesis
Yong Zhang, Le Li, Zhilei Liu +3
Kinship face synthesis is an interesting topic raised to answer questions like "what will your future children look like?". Published approaches to this topic are limited. Most of…