66 citations · 231 across the 31 of their papers we have counts for
18 papers · 1 filter
HairCLIPv2: Unifying Hair Editing via Proxy Feature Blending
Tianyi Wei, Dongdong Chen, Wenbo Zhou +4
Hair editing has made tremendous progress in recent years. Early hair editing methods use well-drawn sketches or masks to specify the editing conditions. Even though they can enabl…
Improving Adversarial Robustness of Masked Autoencoders via Test-time Frequency-domain Prompting
Qidong Huang, Xiaoyi Dong, Dongdong Chen +5
In this paper, we investigate the adversarial robustness of vision transformers that are equipped with BERT pretraining (e.g., BEiT, MAE). A surprising observation is that MAE has…
Test-Time Adaptation for Nighttime Color-Thermal Semantic Segmentation
Yexin Liu, Weiming Zhang, Guoyang Zhao +3
The ability to scene understanding in adverse visual conditions, e.g., nighttime, has sparked active research for RGB-Thermal (RGB-T) semantic segmentation. However, it is essentia…
Diversity-Aware Meta Visual Prompting
Qidong Huang, Xiaoyi Dong, Dongdong Chen +4
We present Diversity-Aware Meta Visual Prompting~(DAM-VP), an efficient and effective prompting method for transferring pre-trained models to downstream tasks with frozen backbone.…
Pseudo Label-Guided Model Inversion Attack via Conditional Generative Adversarial Network
Xiaojian Yuan, Kejiang Chen, Jie Zhang +3
Model inversion (MI) attacks have raised increasing concerns about privacy, which can reconstruct training data from public models. Indeed, MI attacks can be formalized as an optim…
Deep Learning for Event-based Vision: A Comprehensive Survey and Benchmarks
Xu Zheng, Yexin Liu, Yunfan Lu +5
Event cameras are bio-inspired sensors that capture the per-pixel intensity changes asynchronously and produce event streams encoding the time, pixel position, and polarity (sign)…
CLIP Itself is a Strong Fine-tuner: Achieving 85.7% and 88.0% Top-1 Accuracy with ViT-B and ViT-L on ImageNet
Xiaoyi Dong, Jianmin Bao, Ting Zhang +7
Recent studies have shown that CLIP has achieved remarkable success in performing zero-shot inference while its fine-tuning performance is not satisfactory. In this paper, we ident…
X-Paste: Revisiting Scalable Copy-Paste for Instance Segmentation using CLIP and StableDiffusion
Hanqing Zhao, Dianmo Sheng, Jianmin Bao +9
Copy-Paste is a simple and effective data augmentation strategy for instance segmentation. By randomly pasting object instances onto new background images, it creates new training…
Ada3Diff: Defending against 3D Adversarial Point Clouds via Adaptive Diffusion
Kui Zhang, Hang Zhou, Jie Zhang +3
Deep 3D point cloud models are sensitive to adversarial attacks, which poses threats to safety-critical applications such as autonomous driving. Robust training and defend-by-denoi…
PointCAT: Contrastive Adversarial Training for Robust Point Cloud Recognition
Qidong Huang, Xiaoyi Dong, Dongdong Chen +5
Notwithstanding the prominent performance achieved in various applications, point cloud recognition models have often suffered from natural corruptions and adversarial perturbation…
MaskCLIP: Masked Self-Distillation Advances Contrastive Language-Image Pretraining
Xiaoyi Dong, Jianmin Bao, Yinglin Zheng +9
This paper presents a simple yet effective framework MaskCLIP, which incorporates a newly proposed masked self-distillation into contrastive language-image pretraining. The core id…
Bootstrapped Masked Autoencoders for Vision BERT Pretraining
Xiaoyi Dong, Jianmin Bao, Ting Zhang +6
We propose bootstrapped masked autoencoders (BootMAE), a new approach for vision BERT pretraining. BootMAE improves the original masked autoencoders (MAE) with two core designs: 1)…
Invertible Mask Network for Face Privacy-Preserving
Yang Yang, Yiyang Huang, Ming Shi +3
Face privacy-preserving is one of the hotspots that arises dramatic interests of research. However, the existing face privacy-preserving methods aim at causing the missing of seman…
Protecting Celebrities from DeepFake with Identity Consistency Transformer
Xiaoyi Dong, Jianmin Bao, Dongdong Chen +6
In this work we propose Identity Consistency Transformer, a novel face forgery detection method that focuses on high-level semantics, specifically identity information, and detecti…
Shape-invariant 3D Adversarial Point Clouds
Qidong Huang, Xiaoyi Dong, Dongdong Chen +3
Adversary and invisibility are two fundamental but conflict characters of adversarial perturbations. Previous adversarial attacks on 3D point cloud recognition have often been crit…
Self-supervised Transformer for Deepfake Detection
Hanqing Zhao, Wenbo Zhou, Dongdong Chen +2
The fast evolution and widespread of deepfake techniques in real-world scenarios require stronger generalization abilities of face forgery detectors. Some works capture the feature…
E2Style: Improve the Efficiency and Effectiveness of StyleGAN Inversion
Tianyi Wei, Dongdong Chen, Wenbo Zhou +5
This paper studies the problem of StyleGAN inversion, which plays an essential role in enabling the pretrained StyleGAN to be used for real image editing tasks. The goal of StyleGA…
Detection based Defense against Adversarial Examples from the Steganalysis Point of View
Jiayang Liu, Weiming Zhang, Yiwei Zhang +4
Deep Neural Networks (DNNs) have recently led to significant improvements in many fields. However, DNNs are vulnerable to adversarial examples which are samples with imperceptible…