A Deep Cascade Network for Unaligned Face Attribute Classification

نویسندگان

  • Hui Ding
  • Hao Zhou
  • Shaohua Kevin Zhou
  • Rama Chellappa
چکیده

Humans focus attention on different face regions when recognizing face attributes. Most existing face attribute classification methods use the whole image as input. Moreover, some of these methods rely on fiducial landmarks to provide defined face parts. In this paper, we propose a cascade network that simultaneously learns to localize face regions specific to attributes and performs attribute classification without alignment. First, a weakly-supervised face region localization network is designed to automatically detect regions (or parts) specific to attributes. Then multiple part-based networks and a whole-image-based network are separately constructed and combined together by the region switch layer and attribute relation layer for final attribute classification. A multi-net learning method and hint-based model compression is further proposed to get an effective localization model and a compact classification model, respectively. Our approach achieves significantly better performance than state-of-the-art methods on unaligned CelebA dataset, reducing the classification error by 30.9%.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Face Attribute Prediction Using Off-The-Shelf Deep Learning Networks

Predicting attributes from face images in the wild is a challenging computer vision problem. To automatically describe face attributes from face containing images, traditionally one needs to cascade three technical blocks — face localization, facial descriptor construction, and attribute classification — in a pipeline. As a typical classification problem, face attribute prediction has been addr...

متن کامل

Deep or Shallow Facial Descriptors? A Case for Facial Attribute Classification and Face Retrieval

With the largely growing quantity of face images in the social networks and media, different face analyzing systems are developed to be employed in real-world situations such as face recognition, facial expression detection, or automated face tagging. Two demanding face-related applications are studied in this paper: facial attribute classification and face image retrieval. The main common issu...

متن کامل

Attributes for Improved Attributes

We introduce a method for improving facial attribute predictions using other attributes. In the domain of face recognition and verification, attributes are high-level descriptions of face images. Attributes are very useful for identification as well as image search as they provide easily understandable descriptions of faces, rather than most other image descriptors (i.e. HOG, LBP, and SIFT). A ...

متن کامل

Deep Architectures for Face Attributes

We train a deep convolutional neural network to perform identity classification using a new dataset of public figures annotated with age, gender, ethnicity and emotion labels, and then fine-tune it for attribute classification. An optimal sharing pattern of computational resources within this network is determined by experiment, requiring only 1 G flops to produce all predictions. Rather than f...

متن کامل

Deep Attribute Networks

Obtaining compact and discriminative features is one of the major challenges in many of the real-world image classification tasks such as face verification and object recognition. One possible approach is to represent input image on the basis of high-level features that carry semantic meaning which humans can understand. In this paper, a model coined deep attribute network (DAN) is proposed to ...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:
  • CoRR

دوره abs/1709.03851  شماره 

صفحات  -

تاریخ انتشار 2017