Yuhang Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Yuhang Zhang has a total of 25 co-authors. Here are the top co-authors by number of shared publications:
- Weihong Deng
Beijing University of Posts and Telecommunications
6 shared publications - Mei Wang
Beijing Normal University
3 shared publications - Xuannan Liu
Beijing University of Posts and Telecommunications
3 shared publications - Chenyi Liang
Beijing University of Posts and Telecommunications
2 shared publications - Jiani Hu
Beijing University of Posts and Telecommunications
2 shared publications - Lixiong Qin
Beijing University of Posts and Telecommunications
2 shared publications
Latest Publications
- Open Access
- 9 December 2025
- Published by Association for Computing Machinery (ACM) in ACM Computing Surveys
- Vol. 58 (6) , 1-35
Survey on Deep Face Restoration: From Non-blind to Blind and Beyond
Face restoration (FR) is a specialized field within image restoration that aims to recover low-quality (LQ) face images into high-quality (HQ) face images. Recent advances in deep learning technology have led to significant progress in FR methods. In this article, we begin by examining the prevalent factors responsible for real-world LQ images and introduce degradation techniques used to synthesize LQ images. We also discuss notable benchmarks commonly utilized in the field. Next, we categorize FR methods based on different tasks and explain their evolution. Furthermore, we explore the various facial priors commonly utilized in restoration and discuss strategies to enhance their effectiveness. In the experimental section, we thoroughly evaluate the performance of state-of-the-art FR methods across various tasks using a unified benchmark. We analyze their performance from different perspectives. Finally, we discuss real-world applications and challenges faced in the field of FR, propose potential directions for future advancements. The open-source repository corresponding to this work can be found at https://github.com/24wenjie-li/Awesome-Face-Restoration .
- 9 December 2025
- Published by Association for Computing Machinery (ACM) in ACM Computing Surveys
- Vol. 58 (6) , 1-35
Open AccessSurvey on Deep Face Restoration: From Non-blind to Blind and Beyond
Face restoration (FR) is a specialized field within image restoration that aims to recover low-quality (LQ) face images into high-quality (HQ) face images. Recent advances in deep learning technology have led to significant progress in FR methods. In this article, we begin by examining the prevalent factors responsible for real-world LQ images and introduce degradation techniques used to synthesize LQ images. We also discuss notable benchmarks commonly utilized in the field. Next, we categorize FR methods based on different tasks and explain their evolution. Furthermore, we explore the various facial priors commonly utilized in restoration and discuss strategies to enhance their effectiveness. In the experimental section, we thoroughly evaluate the performance of state-of-the-art FR methods across various tasks using a unified benchmark. We analyze their performance from different perspectives. Finally, we discuss real-world applications and challenges faced in the field of FR, propose potential directions for future advancements. The open-source repository corresponding to this work can be found at https://github.com/24wenjie-li/Awesome-Face-Restoration .
- 26 November 2024
- Published by Elsevier in Pattern Recognition
- Vol. 160
Unsupervised evaluation for out-of-distribution detection
- 26 November 2024
- Published by Elsevier in Pattern Recognition
- Vol. 160
Unsupervised evaluation for out-of-distribution detection
- 31 October 2024
- Published by Springer Nature
- p. 240-260
Faceptor: A Generalist Model for Face Perception
- 31 October 2024
- Published by Springer Nature
- p. 240-260
Faceptor: A Generalist Model for Face Perception
- 10 October 2024
- Published by Elsevier in Pattern Recognition
- Vol. 158
AdvCloak: Customized adversarial cloak for privacy protection
- 10 October 2024
- Published by Elsevier in Pattern Recognition
- Vol. 158
AdvCloak: Customized adversarial cloak for privacy protection
- Open Access
Generalizable Facial Expression Recognition
SOTA facial expression recognition (FER) methods fail on test sets that have domain gaps with the train set. Recent domain adaptation FER methods need to acquire labeled or unlabeled samples of target domains to fine-tune the FER model, which might be infeasible in real-world deployment. In this paper, we aim to improve the zero-shot generalization ability of FER methods on different unseen test sets using only one train set. Inspired by how humans first detect faces and then select expression features, we propose a novel FER pipeline to extract expression-related features from any given face images. Our method is based on the generalizable face features extracted by large models like CLIP. However, it is non-trivial to adapt the general features of CLIP for specific tasks like FER. To preserve the generalization ability of CLIP and the high precision of the FER model, we design a novel approach that learns sigmoid masks based on the fixed CLIP face features to extract expression features. To further improve the generalization ability on unseen test sets, we separate the channels of the learned masked features according to the expression classes to directly generate logits and avoid using the FC layer to reduce overfitting. We also introduce a channel-diverse loss to make the learned masks separated. Extensive experiments on five different FER datasets verify that our method outperforms SOTA FER methods by large margins. Code is available in https://github.com/zyh-uaiaaaa/Generalizable-FER.
Open AccessGeneralizable Facial Expression Recognition
SOTA facial expression recognition (FER) methods fail on test sets that have domain gaps with the train set. Recent domain adaptation FER methods need to acquire labeled or unlabeled samples of target domains to fine-tune the FER model, which might be infeasible in real-world deployment. In this paper, we aim to improve the zero-shot generalization ability of FER methods on different unseen test sets using only one train set. Inspired by how humans first detect faces and then select expression features, we propose a novel FER pipeline to extract expression-related features from any given face images. Our method is based on the generalizable face features extracted by large models like CLIP. However, it is non-trivial to adapt the general features of CLIP for specific tasks like FER. To preserve the generalization ability of CLIP and the high precision of the FER model, we design a novel approach that learns sigmoid masks based on the fixed CLIP face features to extract expression features. To further improve the generalization ability on unseen test sets, we separate the channels of the learned masked features according to the expression classes to directly generate logits and avoid using the FC layer to reduce overfitting. We also introduce a channel-diverse loss to make the learned masks separated. Extensive experiments on five different FER datasets verify that our method outperforms SOTA FER methods by large margins. Code is available in https://github.com/zyh-uaiaaaa/Generalizable-FER.
- Open Access
Faceptor: A Generalist Model for Face Perception
With the comprehensive research conducted on various face analysis tasks, there is a growing interest among researchers to develop a unified approach to face perception. Existing methods mainly discuss unified representation and training, which lack task extensibility and application efficiency. To tackle this issue, we focus on the unified model structure, exploring a face generalist model. As an intuitive design, Naive Faceptor enables tasks with the same output shape and granularity to share the structural design of the standardized output head, achieving improved task extensibility. Furthermore, Faceptor is proposed to adopt a well-designed single-encoder dual-decoder architecture, allowing task-specific queries to represent new-coming semantics. This design enhances the unification of model structure while improving application efficiency in terms of storage overhead. Additionally, we introduce Layer-Attention into Faceptor, enabling the model to adaptively select features from optimal layers to perform the desired tasks. Through joint training on 13 face perception datasets, Faceptor achieves exceptional performance in facial landmark localization, face parsing, age estimation, expression recognition, binary attribute classification, and face recognition, achieving or surpassing specialized methods in most tasks. Our training framework can also be applied to auxiliary supervised learning, significantly improving performance in data-sparse tasks such as age estimation and expression recognition. The code and models will be made publicly available at https://github.com/lxq1000/Faceptor.
Open AccessFaceptor: A Generalist Model for Face Perception
With the comprehensive research conducted on various face analysis tasks, there is a growing interest among researchers to develop a unified approach to face perception. Existing methods mainly discuss unified representation and training, which lack task extensibility and application efficiency. To tackle this issue, we focus on the unified model structure, exploring a face generalist model. As an intuitive design, Naive Faceptor enables tasks with the same output shape and granularity to share the structural design of the standardized output head, achieving improved task extensibility. Furthermore, Faceptor is proposed to adopt a well-designed single-encoder dual-decoder architecture, allowing task-specific queries to represent new-coming semantics. This design enhances the unification of model structure while improving application efficiency in terms of storage overhead. Additionally, we introduce Layer-Attention into Faceptor, enabling the model to adaptively select features from optimal layers to perform the desired tasks. Through joint training on 13 face perception datasets, Faceptor achieves exceptional performance in facial landmark localization, face parsing, age estimation, expression recognition, binary attribute classification, and face recognition, achieving or surpassing specialized methods in most tasks. Our training framework can also be applied to auxiliary supervised learning, significantly improving performance in data-sparse tasks such as age estimation and expression recognition. The code and models will be made publicly available at https://github.com/lxq1000/Faceptor.
- Top Cited Papers
- 1 November 2022
- Published by Springer Nature
- p. 418-434
Learn from All: Erasing Attention Consistency for Noisy Label Facial Expression Recognition
- 1 November 2022
- Published by Springer Nature
- p. 418-434
Top Cited PapersLearn from All: Erasing Attention Consistency for Noisy Label Facial Expression Recognition