Search Results for author: Weihong Deng

Found 63 papers, 23 papers with code

Generate to Adapt: Resolution Adaption Network for Surveillance Face Recognition

no code implementations ECCV 2020 Han Fang, Weihong Deng, Yaoyao Zhong, Jiani Hu

Although deep learning techniques have largely improved face recognition, unconstrained surveillance face recognition (FR) is still an unsolved challenge, due to the limited training data and the gap of domain distribution.

Face Recognition Translation

SwinFace: A Multi-task Transformer for Face Recognition, Expression Recognition, Age Estimation and Attribute Estimation

1 code implementation22 Aug 2023 Lixiong Qin, Mei Wang, Chao Deng, Ke Wang, Xi Chen, Jiani Hu, Weihong Deng

To address the conflicts among multiple tasks and meet the different demands of tasks, a Multi-Level Channel Attention (MLCA) module is integrated into each task-specific analysis subnet, which can adaptively select the features from optimal levels and channels to perform the desired tasks.

Age Estimation Face Recognition +1

Enhancing Generalization of Universal Adversarial Perturbation through Gradient Aggregation

1 code implementation ICCV 2023 Xuannan Liu, Yaoyao Zhong, Yuhang Zhang, Lixiong Qin, Weihong Deng

Deep neural networks are vulnerable to universal adversarial perturbation (UAP), an instance-agnostic perturbation capable of fooling the target model for most samples.


Adaptive Face Recognition Using Adversarial Information Network

no code implementations23 May 2023 Mei Wang, Weihong Deng

Supervision on pseudo-labeled samples attracts them towards their prototypes and would cause an intra-domain gap between pseudo-labeled samples and the remaining unlabeled samples within target domain, which results in the lack of discrimination in face recognition.

Domain Generalization Face Recognition +1

CornerFormer: Boosting Corner Representation for Fine-Grained Structured Reconstruction

no code implementations14 Apr 2023 Hongbo Tian, Yulong Li, Linzhi Huang, Yue Yang, Xiangang Li, Weihong Deng

Current transformer-based approaches tackle this challenging problem in a two-stage manner, which detect corners in the first model and classify the proposed edges (corner-pairs) in the second model.

Gradient Attention Balance Network: Mitigating Face Recognition Racial Bias via Gradient Attention

no code implementations5 Apr 2023 Linzhi Huang, Mei Wang, Jiahao Liang, Weihong Deng, Hongzhi Shi, Dongchao Wen, Yingjie Zhang, Jian Zhao

Specifically, we use the gradient attention map (GAM) of the face recognition network to track the sensitive facial regions and make the GAMs of different races tend to be consistent through adversarial learning.

Face Recognition

Semi-Supervised 2D Human Pose Estimation Driven by Position Inconsistency Pseudo Label Correction Module

1 code implementation CVPR 2023 Linzhi Huang, Yulong Li, Hongbo Tian, Yue Yang, Xiangang Li, Weihong Deng, Jieping Ye

The previous method ignored two problems: (i) When conducting interactive training between large model and lightweight model, the pseudo label of lightweight model will be used to guide large models.

2D Human Pose Estimation Pose Estimation +1

Dive into the Resolution Augmentations and Metrics in Low Resolution Face Recognition: A Plain yet Effective New Baseline

1 code implementation11 Feb 2023 Xu Ling, Yichen Lu, Wenqi Xu, Weihong Deng, Yingjie Zhang, Xingchen Cui, Hongzhi Shi, Dongchao Wen

Although deep learning has significantly improved Face Recognition (FR), dramatic performance deterioration may occur when processing Low Resolution (LR) faces.

Face Recognition General Knowledge

Efficient Image Super-Resolution with Feature Interaction Weighted Hybrid Network

no code implementations29 Dec 2022 Wenjie Li, Juncheng Li, Guangwei Gao, Weihong Deng, Jian Yang, Guo-Jun Qi, Chia-Wen Lin

Recently, great progress has been made in single-image super-resolution (SISR) based on deep learning technology.

Image Super-Resolution

Model and Data Agreement for Learning with Noisy Labels

1 code implementation2 Dec 2022 Yuhang Zhang, Weihong Deng, Xingchen Cui, Yunfeng Yin, Hongzhi Shi, Dongchao Wen

We introduce mean point ensemble to utilize a more robust loss function and more information from unselected samples to reduce error accumulation from the model perspective.

Learning with noisy labels

Disentangling Identity and Pose for Facial Expression Recognition

no code implementations17 Aug 2022 Jing Jiang, Weihong Deng

Combining identity and pose feature, a neutral face of input individual should be generated by the decoder.

Disentanglement Face Recognition +2

Learn From All: Erasing Attention Consistency for Noisy Label Facial Expression Recognition

1 code implementation21 Jul 2022 Yuhang Zhang, Chengrui Wang, Xu Ling, Weihong Deng

We find that FER models remember noisy samples by focusing on a part of the features that can be considered related to the noisy labels instead of learning from the whole features that lead to the latent truth.

Facial Expression Recognition Facial Expression Recognition (FER) +1

DH-AUG: DH Forward Kinematics Model Driven Augmentation for 3D Human Pose Estimation

1 code implementation19 Jul 2022 Linzhi Huang, Jiahao Liang, Weihong Deng

To solve this problem, we propose a pose augmentation solution via DH forward kinematics model, which we call DH-AUG. We observe that the previous work is all based on single-frame pose augmentation, if it is directly applied to video pose estimator, there will be several previously ignored problems: (i) angle ambiguity in bone rotation (multiple solutions); (ii) the generated skeleton video lacks movement continuity.

3D Human Pose Estimation

Exploring Disentangled Content Information for Face Forgery Detection

no code implementations19 Jul 2022 Jiahao Liang, Huafeng Shi, Weihong Deng

Convolutional neural network based face forgery detection methods have achieved remarkable results during training, but struggled to maintain comparable performance during testing.


Identifying Rhythmic Patterns for Face Forgery Detection and Categorization

no code implementations4 Jul 2022 Jiahao Liang, Weihong Deng

Motivated by this key observation, we propose a framework for face forgery detection and categorization consisting of: 1) a Spatial-Temporal Filtering Network (STFNet) for PPG signals filtering, and 2) a Spatial-Temporal Interaction Network (STINet) for constraint and interaction of PPG signals.

Deep face recognition with clustering based domain adaptation

no code implementations27 May 2022 Mei Wang, Weihong Deng

Despite great progress in face recognition tasks achieved by deep convolution neural networks (CNNs), these models often face challenges in real world tasks where training images gathered from Internet are different from test images because of different lighting condition, pose and image quality.

Clustering Domain Adaptation +1

Cycle Label-Consistent Networks for Unsupervised Domain Adaptation

no code implementations27 May 2022 Mei Wang, Weihong Deng

The cycle label-consistent loss reinforces the consistency between ground-truth labels and pseudo-labels of source samples leading to statistically similar latent representations between source and target domains.

Unsupervised Domain Adaptation

OPOM: Customized Invisible Cloak towards Face Privacy Protection

1 code implementation24 May 2022 Yaoyao Zhong, Weihong Deng

In this paper, we investigate the face privacy protection from a technology standpoint based on a new type of customized cloak, which can be applied to all the images of a regular user, to prevent malicious face recognition systems from uncovering their identity.

Face Recognition

Oracle-MNIST: a Realistic Image Dataset for Benchmarking Machine Learning Algorithms

1 code implementation19 May 2022 Mei Wang, Weihong Deng

We introduce the Oracle-MNIST dataset, comprising of 28$\times $28 grayscale images of 30, 222 ancient characters from 10 categories, for benchmarking pattern classification, with particular challenges on image noise and distortion.

Benchmarking BIG-bench Machine Learning

Unsupervised Structure-Texture Separation Network for Oracle Character Recognition

1 code implementation13 May 2022 Mei Wang, Weihong Deng, Cheng-Lin Liu

Second, transformation is achieved via swapping the learned textures across domains and a classifier for final classification is trained to predict the labels of the transformed scanned characters.

Disentanglement Unsupervised Domain Adaptation

Meta Balanced Network for Fair Face Recognition

no code implementations13 May 2022 Mei Wang, Yaobin Zhang, Weihong Deng

Finally, to mitigate the algorithmic bias, we propose a novel meta-learning algorithm, called Meta Balanced Network (MBN), which learns adaptive margins in large margin loss such that the model optimized by this loss can perform fairly across people with different skin tones.

Face Recognition Meta-Learning

Domain Generalization via Shuffled Style Assembly for Face Anti-Spoofing

1 code implementation CVPR 2022 Zhuo Wang, Zezheng Wang, Zitong Yu, Weihong Deng, Jiahong Li, Tingting Gao, Zhongyuan Wang

A novel Shuffled Style Assembly Network (SSAN) is proposed to extract and reassemble different content and style features for a stylized feature space.

Contrastive Learning Domain Generalization +1

Video Question Answering: Datasets, Algorithms and Challenges

1 code implementation2 Mar 2022 Yaoyao Zhong, Junbin Xiao, Wei Ji, Yicong Li, Weihong Deng, Tat-Seng Chua

Video Question Answering (VideoQA) aims to answer natural language questions according to the given videos.

Question Answering Video Question Answering

Augmented Geometric Distillation for Data-Free Incremental Person ReID

no code implementations CVPR 2022 Yichen Lu, Mei Wang, Weihong Deng

On this basis, we reveal a "noisy distillation" problem stemming from the noise in dreaming memory, and further propose to augment distillation in a pairwise and cross-wise pattern over different views of memory to mitigate it.

Incremental Learning Person Re-Identification +1

Federated Learning for Face Recognition with Gradient Correction

1 code implementation14 Dec 2021 Yifan Niu, Weihong Deng

With increasing appealing to privacy issues in face recognition, federated learning has emerged as one of the most prevalent approaches to study the unconstrained face recognition problem with private decentralized data.

Face Recognition Federated Learning

Relative Uncertainty Learning for Facial Expression Recognition

1 code implementation NeurIPS 2021 Yuhang Zhang, Chengrui Wang, Weihong Deng

To quantify these uncertainties and achieve good performance under noisy data, we regard uncertainty as a relative concept and propose an innovative uncertainty learning method called Relative Uncertainty Learning (RUL).

Ranked #8 on Facial Expression Recognition (FER) on RAF-DB (Overall Accuracy metric)

Facial Expression Recognition Facial Expression Recognition (FER)

MLFW: A Database for Face Recognition on Masked Faces

no code implementations13 Sep 2021 Chengrui Wang, Han Fang, Yaoyao Zhong, Weihong Deng

As more and more people begin to wear masks due to current COVID-19 pandemic, existing face recognition systems may encounter severe performance degradation when recognizing masked faces.

Face Recognition

Representative Forgery Mining for Fake Face Detection

1 code implementation CVPR 2021 Chengrui Wang, Weihong Deng

Although vanilla Convolutional Neural Network (CNN) based detectors can achieve satisfactory performance on fake face detection, we observe that the detectors tend to seek forgeries on a limited region of face, which reveals that the detectors is short of understanding of forgery.

Data Augmentation Face Detection

Identity-Aware CycleGAN for Face Photo-Sketch Synthesis and Recognition

no code implementations30 Mar 2021 Yuke Fang, Jiani Hu, Weihong Deng

Face photo-sketch synthesis and recognition has many applications in digital entertainment and law enforcement.

Image Generation Sketch Recognition

Face Transformer for Recognition

2 code implementations27 Mar 2021 Yaoyao Zhong, Weihong Deng

Therefore, we investigate the performance of Transformer models in face recognition.

Face Recognition

Selective Pseudo-Labeling with Reinforcement Learning for Semi-Supervised Domain Adaptation

no code implementations7 Dec 2020 Bingyu Liu, Yuhong Guo, Jieping Ye, Weihong Deng

Inspired by the effectiveness of pseudo-labels in domain adaptation, we propose a reinforcement learning based selective pseudo-labeling method for semi-supervised domain adaptation.

Q-Learning reinforcement-learning +3

Point Adversarial Self Mining: A Simple Method for Facial Expression Recognition

no code implementations26 Aug 2020 Ping Liu, Yuewei Lin, Zibo Meng, Lu Lu, Weihong Deng, Joey Tianyi Zhou, Yi Yang

In this paper, we propose a simple yet effective approach, named Point Adversarial Self Mining (PASM), to improve the recognition accuracy in facial expression recognition.

Adversarial Attack Data Augmentation +3

RAF-AU Database: In-the-Wild Facial Expressions with Subjective Emotion Judgement and Objective AU Annotations

no code implementations12 Aug 2020 Wenjing Yan, Shan Li, Chengtao Que, JiQuan Pei, Weihong Deng

Much of the work on automatic facial expression recognition relies on databases containing a certain number of emotion classes and their exaggerated facial configurations (generally six prototypical facial expressions), based on Ekman's Basic Emotion Theory.

Facial Expression Recognition Facial Expression Recognition (FER) +2

Omni-supervised Facial Expression Recognition via Distilled Data

no code implementations18 May 2020 Ping Liu, Yunchao Wei, Zibo Meng, Weihong Deng, Joey Tianyi Zhou, Yi Yang

However, the performance of the current state-of-the-art facial expression recognition (FER) approaches is directly related to the labeled data for training.

Facial Expression Recognition Facial Expression Recognition (FER)

Towards Transferable Adversarial Attack against Deep Face Recognition

no code implementations13 Apr 2020 Yaoyao Zhong, Weihong Deng

In particular, the existence of transferable adversarial examples can severely hinder the robustness of DCNNs since this type of attacks can be applied in a fully black-box manner without queries on the target system.

Adversarial Attack Face Recognition

Mitigate Bias in Face Recognition using Skewness-Aware Reinforcement Learning

no code implementations25 Nov 2019 Mei Wang, Weihong Deng

To encourage fairness, we introduce the idea of adaptive margin to learn balanced performance for different races based on large margin losses.

Face Recognition Fairness +3

Metric Classification Network in Actual Face Recognition Scene

no code implementations25 Oct 2019 Jian Li, Yan Wang, Xiubao Zhang, Weihong Deng, Haifeng Shen

In this paper, we train a validation classifier to normalize the decision threshold, which means that the result can be obtained directly without replacing the threshold.

Classification Face Recognition +2

Adversarial Learning with Margin-based Triplet Embedding Regularization

1 code implementation ICCV 2019 Yaoyao Zhong, Weihong Deng

The Deep neural networks (DNNs) have achieved great success on a variety of computer vision tasks, however, they are highly vulnerable to adversarial attacks.

Classification Face Recognition +1

Mixed High-Order Attention Network for Person Re-Identification

1 code implementation ICCV 2019 Binghui Chen, Weihong Deng, Jiani Hu

Then, rethinking person ReID as a zero-shot learning problem, we propose the Mixed High-Order Attention Network (MHN) to further enhance the discrimination and richness of attention knowledge in an explicit manner.

Person Re-Identification Vocal Bursts Intensity Prediction +1

Hybrid-Attention based Decoupled Metric Learning for Zero-Shot Image Retrieval

no code implementations CVPR 2019 Binghui Chen, Weihong Deng

In zero-shot image retrieval (ZSIR) task, embedding learning becomes more attractive, however, many methods follow the traditional metric learning idea and omit the problems behind zero-shot settings.

Image Retrieval Metric Learning +2

A Deeper Look at Facial Expression Dataset Bias

no code implementations25 Apr 2019 Shan Li, Weihong Deng

Datasets play an important role in the progress of facial expression recognition algorithms, but they may suffer from obvious biases caused by different cultures and collection conditions.

Facial Expression Recognition Facial Expression Recognition (FER)

Signal-to-Noise Ratio: A Robust Distance Metric for Deep Metric Learning

no code implementations CVPR 2019 Tongtong Yuan, Weihong Deng, Jian Tang, Yinan Tang, Binghui Chen

In this paper, different from the approaches on learning the loss structures, we propose a robust SNR distance metric based on Signal-to-Noise Ratio (SNR) for measuring the similarity of image pairs for deep metric learning.

Clustering Image Clustering +4

Energy Confused Adversarial Metric Learning for Zero-Shot Image Retrieval and Clustering

no code implementations22 Jan 2019 Binghui Chen, Weihong Deng

However, in this paper, we first emphasize that the generalization ability is a core ingredient of this 'good' embedding as well and largely affects the metric performance in zero-shot settings as a matter of fact.

Clustering Image Retrieval +3

Virtual Class Enhanced Discriminative Embedding Learning

1 code implementation NeurIPS 2018 Binghui Chen, Weihong Deng, Haifeng Shen

Recently, learning discriminative features to improve the recognition performances gradually becomes the primary goal of deep learning, and numerous remarkable works have emerged.

Face Verification General Classification

Learning Better Features for Face Detection with Feature Fusion and Segmentation Supervision

no code implementations20 Nov 2018 Wanxin Tian, Zixuan Wang, Haifeng Shen, Weihong Deng, Yiping Meng, Binghui Chen, Xiubao Zhang, Yuan Zhao, Xiehe Huang

We assume that problems inside are inadequate use of supervision information and imbalance between semantics and details at all level feature maps in CNN even with Feature Pyramid Networks (FPN).

Face Detection Semantic Segmentation

ALMN: Deep Embedding Learning with Geometrical Virtual Point Generating

no code implementations4 Jun 2018 Binghui Chen, Weihong Deng

Deep embedding learning becomes more attractive for discriminative feature learning, but many methods still require hard-class mining, which is computationally complex and performance-sensitive.

Clustering Image Retrieval +2

Deep Facial Expression Recognition: A Survey

7 code implementations23 Apr 2018 Shan Li, Weihong Deng

We then introduce the available datasets that are widely used in the literature and provide accepted data selection and evaluation principles for these datasets.

Facial Expression Recognition Facial Expression Recognition (FER)

Deep Face Recognition: A Survey

6 code implementations18 Apr 2018 Mei Wang, Weihong Deng

Deep learning applies multiple processing layers to learn representations of data with multiple levels of feature extraction.

Face Recognition Face Verification +1

Deep Visual Domain Adaptation: A Survey

no code implementations10 Feb 2018 Mei Wang, Weihong Deng

Deep domain adaption has emerged as a new learning technique to address the lack of massive amounts of labeled data.

Domain Adaptation Face Recognition +4

Cross-Age LFW: A Database for Studying Cross-Age Face Recognition in Unconstrained Environments

no code implementations28 Aug 2017 Tianyue Zheng, Weihong Deng, Jiani Hu

Labeled Faces in the Wild (LFW) database has been widely utilized as the benchmark of unconstrained face verification and due to big data driven machine learning methods, the performance on the database approaches nearly 100%.

Face Recognition Face Verification +1

Noisy Softmax: Improving the Generalization Ability of DCNN via Postponing the Early Softmax Saturation

no code implementations CVPR 2017 Binghui Chen, Weihong Deng, Junping Du

In this paper, we first emphasize that the early saturation behavior of softmax will impede the exploration of SGD, which sometimes is a reason for model converging at a bad local-minima, then propose Noisy Softmax to mitigating this early saturation issue by injecting annealed noise in softmax during each iteration.

Reliable Crowdsourcing and Deep Locality-Preserving Learning for Expression Recognition in the Wild

no code implementations CVPR 2017 Shan Li, Weihong Deng, JunPing Du

Past research on facial expressions have used relatively limited datasets, which makes it unclear whether current methods can be employed in real world.

Generative Model with Coordinate Metric Learning for Object Recognition Based on 3D Models

no code implementations24 May 2017 Yida Wang, Weihong Deng

In this paper, our generative model trained with synthetic images rendered from 3D models reduces the workload of data collection and limitation of conditions.

Bayesian Inference Metric Learning +2

Multi-Manifold Deep Metric Learning for Image Set Classification

no code implementations CVPR 2015 Jiwen Lu, Gang Wang, Weihong Deng, Pierre Moulin, Jie zhou

In this paper, we propose a multi-manifold deep metric learning (MMDML) method for image set classification, which aims to recognize an object of interest from a set of image instances captured from varying viewpoints or under varying illuminations.

Classification General Classification +1

Linear Ranking Analysis

no code implementations CVPR 2014 Weihong Deng, Jiani Hu, Jun Guo

We extend the classical linear discriminant analysis (LDA) technique to linear ranking analysis (LRA), by considering the ranking order of classes centroids on the projected subspace.

Zero-Shot Learning

In Defense of Sparsity Based Face Recognition

no code implementations CVPR 2013 Weihong Deng, Jiani Hu, Jun Guo

The success of sparse representation based classification (SRC) has largely boosted the research of sparsity based face recognition in recent years.

Face Recognition Sparse Representation-based Classification

Cannot find the paper you are looking for? You can Submit a new open access paper.