no code implementations • 20 Apr 2024 • Zhengcong Fei, Mingyuan Fan, Junshi Huang
Consistency models have exhibited remarkable capabilities in facilitating efficient image/video generation, enabling synthesis with minimal sampling steps.
1 code implementation • 6 Apr 2024 • Zhengcong Fei, Mingyuan Fan, Changqian Yu, Debang Li, Junshi Huang
Transformers have catalyzed advancements in computer vision and natural language processing (NLP) fields.
1 code implementation • 8 Feb 2024 • Zhengcong Fei, Mingyuan Fan, Changqian Yu, Junshi Huang
We endeavor to train diffusion models for image data, wherein the traditional U-Net backbone is supplanted by a state space backbone, functioning on raw patches or latent space.
no code implementations • 22 Dec 2023 • Xiaoyue Duan, Shuhao Cui, Guoliang Kang, Baochang Zhang, Zhengcong Fei, Mingyuan Fan, Junshi Huang
Consistent editing of real images is a challenging task, as it requires performing non-rigid edits (e. g., changing postures) to the main objects in the input image without changing their identity or attributes.
no code implementations • 27 Nov 2023 • Zhengcong Fei, Mingyuan Fan, Junshi Huang
The target representations of those regions are extracted by the exponential moving average of context encoder, \emph{i. e.}, target encoder, on the whole spectrogram.
no code implementations • 10 Nov 2023 • Mingyuan Fan, Xiaodan Li, Cen Chen, Yinggui Wang
We reveal that input regularization based methods make resultant adversarial examples biased towards flat extreme regions.
no code implementations • 31 Jul 2023 • Mingyuan Fan, Chengyu Wang, Cen Chen, Yang Liu, Jun Huang
Diffusion models and large language models have emerged as leading-edge generative models, revolutionizing various aspects of human life.
no code implementations • 16 Jul 2023 • Mingyuan Fan, Cen Chen, Chengyu Wang, Wenmeng Zhou, Jun Huang
Split learning enables collaborative deep learning model training while preserving data privacy and model security by avoiding direct sharing of raw data and model details (i. e., sever and clients only hold partial sub-networks and exchange intermediate computations).
no code implementations • 12 Apr 2023 • Zhengcong Fei, Mingyuan Fan, Junshi Huang
Recent works on personalized text-to-image generation usually learn to bind a special token with specific subjects or styles of a few given images by tuning its embedding through gradient descent.
1 code implementation • CVPR 2023 • Zhengcong Fei, Mingyuan Fan, Li Zhu, Junshi Huang, Xiaoming Wei, Xiaolin Wei
In this paper, we introduce a novel Generative Adversarial Networks alike framework, referred to as GAN-MAE, where a generator is used to generate the masked patches according to the remaining visible patches, and a discriminator is employed to predict whether the patch is synthesized by the generator.
no code implementations • 5 Dec 2022 • Mingyuan Fan, Cen Chen, Chengyu Wang, Xiaodan Li, Wenmeng Zhou, Jun Huang
Recent works have brought attention to the vulnerability of Federated Learning (FL) systems to gradient leakage attacks.
no code implementations • 30 Nov 2022 • Zhengcong Fei, Mingyuan Fan, Li Zhu, Junshi Huang, Xiaoming Wei, Xiaolin Wei
It is well believed that the higher uncertainty in a word of the caption, the more inter-correlated context information is required to determine it.
no code implementations • 5 Oct 2022 • Zhengcong Fei, Mingyuan Fan, Li Zhu, Junshi Huang
Recently, Vector Quantized AutoRegressive (VQ-AR) models have shown remarkable results in text-to-image synthesis by equally predicting discrete image tokens from the top left to bottom right in the latent space.
1 code implementation • 13 Aug 2022 • Mingyuan Fan, Cen Chen, Ximeng Liu, Wenzhong Guo
By contrast, we re-formulate crafting transferable AEs as the maximizing a posteriori probability estimation problem, which is an effective approach to boost the generalization of results with limited available data.
no code implementations • 13 Aug 2022 • Mingyuan Fan, Yang Liu, Cen Chen, Ximeng Liu, Wenzhong Guo
The opacity of neural networks leads their vulnerability to backdoor attacks, where hidden attention of infected neurons is triggered to override normal predictions to the attacker-chosen ones.
no code implementations • 20 Apr 2022 • Mingyuan Fan, Yang Liu, Cen Chen
Specifically, the intuition stems from the fact that a very limited part of informative samples can contribute to most of model performance.
no code implementations • 28 Feb 2022 • Mingyuan Fan, Wenzhong Guo, Shengxing Yu, Zuobin Ying, Ximeng Liu
Transferability of adversarial examples is of critical importance to launch black-box adversarial attacks, where attackers are only allowed to access the output of the target model.
no code implementations • 24 Jan 2022 • Yang Liu, Mingyuan Fan, Cen Chen, Ximeng Liu, Zhuo Ma, Li Wang, Jianfeng Ma
First, trigger pattern recovery is conducted to extract the trigger patterns infected by the victim model.
6 code implementations • CVPR 2021 • Mingyuan Fan, Shenqi Lai, Junshi Huang, Xiaoming Wei, Zhenhua Chai, Junfeng Luo, Xiaolin Wei
BiSeNet has been proved to be a popular two-stream network for real-time segmentation.
Ranked #8 on Real-Time Semantic Segmentation on Cityscapes test