In recent years, researchers have proposed many deep learning (DL) methods for various tasks, and particularly face recognition (FR) made an enormous leap using these techniques. Deep FR systems benefit from the hierarchical architecture of the DL methods to learn discriminative face representation. Therefore, DL techniques significantly improve state-of-the-art performance on FR systems and encourage diverse and efficient real-world applications. In this paper, we present a comprehensive analysis of various FR systems that leverage the different types of DL techniques, and for the study, we summarize 171 recent contributions from this area. We discuss the papers related to different algorithms, architectures, loss functions, activation functions, datasets, challenges, improvement ideas, current and future trends of DL-based FR systems. We provide a detailed discussion of various DL methods to understand the current state-of-the-art, and then we discuss various activation and loss functions for the methods. Additionally, we summarize different datasets used widely for FR tasks and discuss challenges related to illumination, expression, pose variations, and occlusion. Finally, we discuss improvement ideas, current and future trends of FR tasks.

Recent Advances in Deep Learning Techniques for Face Recognition

Learning features from covariance matrix of gabor wavelet for face recognition under adverse conditions

Intelligent video surveillance is an important computer vision application in natural environments. Since detected objects under surveillance are usually low-resolution and noisy, their accurate recognition represents a huge challenge. Knowledge distillation is an effective method to deal with it, but existing related work usually focuses on reducing the channel count of a student network, not feature map size. As a result, they cannot transfer "privilege information" hidden in feature maps of a wide and deep teacher network into a thin and shallow student one, leading to the latter's poor performance. To address this issue, we propose a Feature Map Distillation (FMD) framework under which the feature map size of teacher and student networks is different. FMD consists of two main components: Feature Decoder Distillation (FDD) and Feature Map Consistency-enforcement (FMC). FDD reconstructs the shallow texture features of a thin student network to approximate the corresponding samples in a teacher network, which allows the high-resolution ones to directly guide the learning of the shallow features of the student network. FMC makes the size and direction of each deep feature map consistent between student and teacher networks, which constrains each pair of feature maps to produce the same feature distribution. FDD and FMC allow a thin student network to learn rich "privilege information" in feature maps of a wide teacher network. The overall performance of FMD is verified in multiple recognition tasks by comparing it with state-of-the-art knowledge distillation methods on low-resolution and noisy objects. 

Feature Map Distillation of Thin Nets for Low-Resolution Object Recognition

Face recognition has long been an active research area in the field of artificial intelligence, particularly since the rise of deep learning in recent years. In some practical situations, each identity has only a single sample available for training. Face recognition under this situation is referred to as single sample face recognition and poses significant challenges to the effective training of deep models. Therefore, in recent years, researchers have attempted to unleash more potential of deep learning and improve the model recognition performance in the single sample situation. While several comprehensive surveys have been conducted on traditional single sample face recognition approaches, emerging deep learning based methods are rarely involved in these reviews. Accordingly, we focus on the deep learning-based methods in this paper, classifying them into virtual sample methods and generic learning methods. In the former category, virtual images or virtual features are generated to benefit the training of the deep model. In the latter one, additional multi-sample generic sets are used. There are three types of generic learning methods: combining traditional methods and deep features, improving the loss function, and improving network structure, all of which are covered in our analysis. Moreover, we review face datasets that have been commonly used for evaluating single sample face recognition models and go on to compare the results of different types of models. Additionally, we discuss problems with existing single sample face recognition methods, including identity information preservation in virtual sample methods, domain adaption in generic learning methods. Furthermore, we regard developing unsupervised methods is a promising future direction, and point out that the semantic gap as an important issue that needs to be further considered. 

Deep learning based single sample face recognition: a survey

Most of research studies that have dealt with face corrupted images to the level of being unrecognizable by a human are based on full image reconstruction. In some real scenarios, a single corrupted image might need to be recognized among a limited number of available clean images. This study deals with face identification from artificially corrupted images with various kinds of noises. The work proposes a face identification conditional generative adversarial network (FI-CGAN) model to identify faces based on the CGAN. The proposed models reconstruct the corrupted image based on available clean images to map the corrupted image to a specific label. The classification is made using the nearest neighbor method with peak signal-to-noise ratio, mean squared error and structural similarity index as metrics. The study used the Specs on Faces dataset and achieved a satisfactory performance for face identification. 

https://academic.oup.com/ijnp/article-pdf/25/4/269/43396983/pyab084.pdf

OUP accepted manuscript

Although deep learning-based face recognition techniques have achieved amazing performance in recent years, low-resolution (LR) face recognition remains challenging. In this letter, we address this problem by proposing an identity-aware face super-resolution network to recover identity information of LR faces. To learn identity-aware features effectively, the identity features are explicitly disentangled to two orthogonal components: the magnitude and angle of features that project identity features to a hypersphere space. We show that the magnitude of features is related to the quality of a face. The proposed approach shows its superiority on recovering identity-related textures which are beneficial to recover identity information for recognition. Extensive experiments demonstrate the effectiveness of the proposed algorithm in LR face recognition.

Identity-Aware Face Super-Resolution for Low-Resolution Face Recognition

One-shot face recognition has attracted extensive attention with the ability to recognize persons at just one glance. With only one training sample which cannot represent intra-class variance adequately, one-shot classes have poor generalization ability, and it is difficult to obtain appropriate classification weights. In this paper, we explore an inherent relationship between features and classification weights. In detail, we propose feature rectification generative adversarial network (FR-GAN) which is able to rectify features closer to corresponding classification weights considering existing classification weights information. With one model, we achieve two purposes: without fine-tuning via back propagation as previous CNN approaches which are time consuming and computationally expensive, FR-GAN can not only (1) generate classification weights for new classes using training data, but also (2) achieve more discriminative test feature representation. The experimental results demonstrate the remarkable performance of our proposed method, as in MS-Celeb-1M one-shot benchmark, our method achieves 93.12% coverage at 99% precision with the introduction of novel classes and remains a high accuracy at 99.80% for base classes, surpassing most of the previous approaches based on fine-tuning.

One-Shot Face Recognition with Feature Rectification via Adversarial Learning

The invention relates to a depth feature representation method based on multiple stacked auto-encoding. Feature expressions of different hierarchical structures of a target object are acquired through constructing stacked auto-encoding networks of different structures. A shallow-layer (the number of hidden layers is smaller) neural network structure is constructed, a back-propagation method is adopted to train network parameters to enable a neural network to achieve the optimal structure, and outputs, namely the feature expressions, of a second layer of the network are acquired; more deeply hierarchical network structures are respectively established, network parameters are trained according to a similar manner, and thus outputs (the feature expressions) of corresponding layers are acquired; and fusion and selection are carried out on the above-mentioned obtained features according to a manner of feature combination and selection to acquire a hierarchical feature representation that characterizes a target. Therefore, corresponding visual tasks (image classification, identification and detection) are carried out.

Depth feature representation method based on multiple stacked auto-encoding

The invention provides a target tracking method and system based on locus optimization. The target tracking method based on locus optimization comprises steps of constructing a target model in a firstframe, performing sample sampling on a target, marking the sample according to a coverage ratio with the target, extracting a multi-fused characteristic training structured classifier according to obtain a basic target model, adopting a plurality candidates in following frame images, using each candidate to train the model, choosing a candidate having a highest confident coefficient in a next frame, and after iterating multiple frames like this, choosing an optimal motion short locus of the target according to an average confidence coefficient of multiple loci constructed in continuous multiple frames. As a result, the target tracking method and system based on locus optimization overcome problems that a conventional method based on static detection causes a fact that a model lacks of determination capability because of overlooking space-time information and thus cannot choose an optimal target and thus causes model deviation. Furthermore, a structured output classification model based on multi-characteristic fusion can effectively improve an identification ability of the model.

Target tracking method and system based on locus optimization

Handle everyday research tasks with reliable, citation-backed results

Your personal Research Agent to handle research tasks with citation-backed results

Popular Tasks used by Researchers

How can I help with your research?

Meet SciSpace

Get more enhanced response by uploading the PDFs you want me to reference.

No relevant PDFs in your library

SciSpace is the AI research assistant for academics. Run systematic literature reviews on 280M+ papers, and write papers with cited sources. Trusted by 1M+ students, PhDs & researchers.

SciSpace | AI for Research

Analyze PDFs

Code & Manuscripts

Funding & Grants

Literature & Patents

Medical & Clinical Data

Systematic Review

Visualize & Present

Web & Data

Build a Google Scholar-like website for your research.

Build a website

Create charts and images for your research

Create a Chart

Write a paper for submission to a journal

Draft a manuscript

Patent Search

Design eye-catching scientific posters in minutes.

Scientific Poster Generation

Systematic Literature Review

One task is running at the moment. Your messages will be shown right after.

Drag and drop or click here to browse

Loved by <highlight>1 million+</highlight> researchers

Extract a list of specific topics and their sources from unstructured text

Topics

Compare and analyze relevant papers that matches with your search

Papers

Get insights from PDFs and bookmarked papers from your library

My library

Recent searches

Try searching for:

Catch AI-generated content in scholarly and non-scholarly content

{ai} Detector

Ai Writer

Get PDF Summaries, highlighted text explanations 

Chat with PDF

Effortlessly create in-text citations and bibliographies in APA and 2,500 other formats

Citation generator

Get explanations, summaries, and answers on academic papers

Ease up your research workflow with {scispace}'s cohort of exciting AI tools

Elevate your academic writing skills and convey your ideas the way you want

Paraphraser

Explore our range of reading and writing tools

Your file is being prepared and should be ready in a few minutes. If it's a large file, it might take a bit longer. You can close this window, and we'll email you the file when it's done.

You have reached a maximum limit of <strong>{limit}</strong> columns in the table. Remove at least <strong>1</strong> column to add or create another one.

Chen Jin

Author Tools

Chat about Author

Papers

Identity-Aware Face Super-Resolution for Low-Resolution Face Recognition

One-Shot Face Recognition with Feature Rectification via Adversarial Learning

Depth feature representation method based on multiple stacked auto-encoding

Target tracking method and system based on locus optimization