Disentanglement for Discriminative Visual Recognition

06/14/2020
by   Xiaofeng Liu, et al.
0

Recent successes of deep learning-based recognition rely on maintaining the content related to the main-task label. However, how to explicitly dispel the noisy signals for better generalization in a controllable manner remains an open issue. For instance, various factors such as identity-specific attributes, pose, illumination and expression affect the appearance of face images. Disentangling the identity-specific factors is potentially beneficial for facial expression recognition (FER). This chapter systematically summarize the detrimental factors as task-relevant/irrelevant semantic variations and unspecified latent variation. In this chapter, these problems are casted as either a deep metric learning problem or an adversarial minimax game in the latent space. For the former choice, a generalized adaptive (N+M)-tuplet clusters loss function together with the identity-aware hard-negative mining and online positive mining scheme can be used for identity-invariant FER. The better FER performance can be achieved by combining the deep metric loss and softmax loss in a unified two fully connected layer branches framework via joint optimization. For the latter solution, it is possible to equipping an end-to-end conditional adversarial network with the ability to decompose an input sample into three complementary parts. The discriminative representation inherits the desired invariance property guided by prior knowledge of the task, which is marginal independent to the task-relevant/irrelevant semantic and latent variations. The framework achieves top performance on a serial of tasks, including lighting, makeup, disguise-tolerant face recognition and facial attributes recognition. This chapter systematically summarize the popular and practical solution for disentanglement to achieve more discriminative visual recognition.

READ FULL TEXT

page 2

page 3

page 4

page 21

page 26

research
09/15/2023

Unsupervised Disentangling of Facial Representations with 3D-aware Latent Diffusion Models

Unsupervised learning of facial representations has gained increasing at...
research
02/23/2020

DotFAN: A Domain-transferred Face Augmentation Network for Pose and Illumination Invariant Face Recognition

The performance of a convolutional neural network (CNN) based face recog...
research
01/01/2021

Identity-aware Facial Expression Recognition in Compressed Video

This paper targets to explore the inter-subject variations eliminated fa...
research
11/28/2017

An Adversarial Neuro-Tensorial Approach For Learning Disentangled Representations

Several factors contribute to the appearance of an object in a visual sc...
research
10/20/2020

Mutual Information Regularized Identity-aware Facial ExpressionRecognition in Compressed Video

This paper targets to explore the inter-subject variations eliminated fa...
research
12/27/2015

Improving Facial Analysis and Performance Driven Animation through Disentangling Identity and Expression

We present techniques for improving performance driven facial animation,...
research
10/15/2020

THIN: THrowable Information Networks and Application for Facial Expression Recognition In The Wild

For a number of tasks solved using deep learning techniques, an exogenou...

Please sign up or login with your details

Forgot password? Click here to reset