We present a multi-task learning-based convolutional neural network (MTL-CNN) able to estimate multiple tags describing face images simultaneously. In total, the model is able to estimate up to 74 different face attributes belonging to three distinct recognition tasks: age group, gender and visual attributes (such as hair color, face shape and the presence of makeup). The proposed model shares all the CNN’s parameters among tasks and deals with task-specific estimation through the introduction of two components: (i) a gating mechanism to control activations’ sharing and to adaptively route them across different face attributes; (ii) a module to post-process the predictions in order to take into account the correlation among face attributes. The model is trained by fusing multiple databases for increasing the number of face attributes that can be estimated and using a center loss for disentangling representations among face attributes in the embedding space. Extensive experiments validate the effectiveness of the proposed approach.

https://www.mdpi.com/1424-8220/18/8/2666/pdf

Fine-Grained Face Annotation Using Deep Multi-Task CNN

Recognizing face attributes in the wild is a challenging problem. With the development of embedded devices, smart phone and deep learning, face attributes recognition based on deep learning has raised increasing attention. Accuracy and efficiency are the two key-points in any application which uses these face attributes as an aid system. In most of the previous papers, multi-independency classifiers are proposed; and most of them just focus on accurate rate while neglecting efficiency. This paper proposes a horizontal pyramid global convolution (HPGC) module as feature mapping operator to extract more local information; designs a light-weight attribute convolution neural network (LACNN) combining with HPGC; and utilizes sigmoid cross entropy loss function for improving the accuracy and efficiency of the face attributes recognition model. Replacing full connection or global average pooling with the proposed HPGC module, we balance the accuracy performance and computation cost. As a result, we not only get high accuracy but also reduce the computational cost. Extensive experiments results on two widely used face attribute datasets, LFW and CelebA, demonstrate that our LACNN-HPGC framework achieves significantly improved efficiency compared with state-of-the-art lightweight models for face attributes recognition.

Real-time face attributes recognition via HPGC: horizontal pyramid global convolution

Every day, a large number of digital images are produced by users of social networks, smartphone users, photography professionals, etc. This caused a problem in the management, organization, indexing, and recovery of digital images. In order to ease this problem, several methods have been introduced in the literature to catalog images automatically. These methods are designed to associate images with one or more keywords belonging to a predefined dictionary or to associate images with visual attributes such as, for example, quality, aesthetics, sentiment, memorability, interestingness, and complexity, etc. This thesis investigates the use of deep convolutional neural network for automatic estimation of image quality and image aesthetics. In the last few years, several methods for automatic image quality assessment have been proposed. Most of them have been designed to deal with synthetically distorted images, which by definition do not truly model distortions afflicting real-world images. In this thesis a method for the automatic quality assessment of authentically distorted images is investigated. It shows better performances than state-of-the-art methods both on synthetically and authentically distorted images datasets. Differently from the image quality, which characterizes the perceived quality of the image signal, aesthetics depicts perceived beauty. As first step, the problem of aesthetic quality assessment of real-life general content images has been investigated. The proposed solution outperformed state-of-the-art methods on the largest publicly available dataset. Given that one of the most popular visual contents is the face (e.g. on social networks for photo sharing), aesthetics assessment is, therefore, further investigated on the specific case of portrait images. To this end, in this thesis an algorithm involving the combination of the previously investigated visual attributes (i.e. quality and aesthetics of general content images) and the facial attributes (i.e. smiling, hair style, makeup) description is proposed. Facial attributes description is achieved thanks to two proposed methods. The first algorithm is a robust smile detector (it represents an important visual feature for portrait aesthetics), the second is a multiple-task model designed in order to simultaneously estimate soft biometrics and attributes such as hair colors and styles, types of beards. While the first algorithm outperforms state-of-the-art methods (also respect to highly distorted images), the multi-task model demonstrates comparable performance. Experimental results for the portrait image aesthetic assessment thanks to the use of the proposed algorithm show promising performance on three standard datasets.

Learning quality, aesthetics, and facial attributes for image annotation

Face attribute recognition plays a vital role in face-related tasks. Common face attributes include person age, person gender, mask-wearing, glasses-wearing, etc. Using one network to predict all attributes can save many computation costs. However, these attributes can hardly be fully labelled on every image in the same dataset since the labelling costs and the requirement on the sample balance. In many cases, each of the datasets are labelled with a single attribute. With several such datasets, how to use one network to generate the multi-task predictions for all attributes is a problem. In this paper, we propose a two-level iteration training method for multi-task face attribute learning with task-isolated labels. The two-level iteration method includes a task-level inner iteration and the regular outer iteration. With this scheme, the network receives the gradients from all tasks after each inner iteration. After training, the network is able to predict all attributes. Experiments show the effectiveness of the method and the advantages of multi-task learning over single-task learning on network accuracy and efficiency, which demonstrate the broad applicability and effectiveness of the proposed approach.

Two-level iteration method for multi-task learning with task-isolated labels

In this abstract, we introduce the MTL-CNN, a multi-task learning-based multilayer neuronal net that can concurrently calculate multiple items for facial image. Age range, gender, & visual features make up the model's overall capacity to assess up to 74 different appearance characteristics from 3 distinct detection tests . The suggested framework introduces 2 parts: I a gating method to govern activation distribution & to flexibly route these among various appearance qualities; and (ii) a modules to comment the forecasts in addition to taking into consideration the connection between face qualities. This model distributes all the CNN's characteristics between assignments and handles with undertaking estimates. The model is developed by combining different database to increase the amount of facial qualities that can be evaluated, and by utilizing a center loss to unify presentations of different facial characteristics inside the embed region. Numerous tests confirm that the suggested strategy works. 

Accurate Face Annotations utilizing Deep CNN

Predicting face attributes in images is challenging due to complex face variations. We observe that the signals of some attributes are strong in roughly fixed facial area. In this paper, we propose a deep multi-task cascaded network for face attributes recognition, which is trained in an end-to-end way by the combination of attribute-associated region discovery and attribute prediction together. Associated region is mapped by the first sub-network, which is a fully convolutional network (FCN). Then the second sub-network takes the arbitrary-sized associated regions as input. We use RoI pooling to transform them into a uniform-sized region, and train the whole model by stochastic gradient descent (SGD). We also introduce several useful training strategies, including the batch sampling and the early stopping. We adopt sample augmentation for the balance of positive and negative training data in batch sampling. We involve the early stopping to terminate the iterations flexibly for each attribute in case of the model deviation caused by the overfitting of easy attributes. We evaluate our model on two widely used attributes recognition databases, and the experimental results demonstrate that the performance of our approach is better than other state-of-the-art methods on the most of face attributes.

Face Attributes Recognition via Deep Multi-Task Cascade

Popular Tasks used by Researchers

How can I help with your research?

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

We encountered an error while loading the panel. Please try refreshing the page.

Something went wrong

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

Anyone with the link can view this chat. You can switch it back to private anytime.

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.

Hui Cheng

Author Tools

Chat about Author

Papers

Face Attributes Recognition via Deep Multi-Task Cascade