Exploring Disentangled Feature Representation Beyond Face Identification

Liu, Yu; Wei, Fangyin; Shao, Jing; Sheng, Lu; Yan, Junjie; Wang, Xiaogang

doi:10.1109/cvpr.2018.00222

Cited by 155 publications

(93 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The [9] developed an adversarial UV completion framework (UV-GAN) to solve the pose invariant face recognition problem. The [32] proposed to learn the identitydistilled features and the identity-dispelled features in an adversarial autoencoder framework. The [58] proposed an adversarial network to generate hard triplet feature examples.…”

Section: Related Workmentioning

confidence: 99%

Decorrelated Adversarial Learning for Age-Invariant Face Recognition

Wang

Gong

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

View full text Add to dashboard Cite

There has been an increasing research interest in ageinvariant face recognition. However, matching faces with big age gaps remains a challenging problem, primarily due to the significant discrepancy of face appearances caused by aging. To reduce such a discrepancy, in this paper we propose a novel algorithm to remove age-related components from features mixed with both identity and age information. Specifically, we factorize a mixed face feature into two uncorrelated components: identity-dependent component and age-dependent component, where the identitydependent component includes information that is useful for face recognition. To implement this idea, we propose the Decorrelated Adversarial Learning (DAL) algorithm, where a Canonical Mapping Module (CMM) is introduced to find the maximum correlation between the paired features generated by a backbone network, while the backbone network and the factorization module are trained to generate features reducing the correlation. Thus, the proposed model learns the decomposed features of age and identity whose correlation is significantly reduced. Simultaneously, the identity-dependent feature and the age-dependent feature are respectively supervised by ID and age preserving signals to ensure that they both contain the correct information. Extensive experiments are conducted on popular public-domain face aging datasets (FG-NET, MORPH Album 2, and CACD-VS) to demonstrate the effectiveness of the proposed approach.

show abstract

Section: Related Workmentioning

confidence: 99%

Decorrelated Adversarial Learning for Age-Invariant Face Recognition

Wang

Gong

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

View full text Add to dashboard Cite

show abstract

“…recently as it is a prerequisite in many computer vision applications. For example, facial landmark detection can be applied to a large variety of tasks, including face recognition [74,30], head pose estimation [58], facial reenactment [53] and 3D face reconstruction [28], to name a few.…”

Section: Introductionmentioning

confidence: 99%

Style Aggregated Network for Facial Landmark Detection

Dong

Yan

Ouyang

et al. 2018

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition

286

212

View full text Add to dashboard Cite

Recent advances in facial landmark detection achieve success by learning discriminative features from rich deformation of face shapes and poses. Besides the variance of faces themselves, the intrinsic variance of image styles, e.g., grayscale vs. color images, light vs. dark, intense vs. dull, and so on, has constantly been overlooked. This issue becomes inevitable as increasing web images are collected from various sources for training neural networks. In this work, we propose a style-aggregated approach to deal with the large intrinsic variance of image styles for facial landmark detection. Our method transforms original face images to style-aggregated images by a generative adversarial module. The proposed scheme uses the style-aggregated image to maintain face images that are more robust to environmental changes. Then the original face images accompanying with style-aggregated ones play a duet to train a landmark detector which is complementary to each other. In this way, for each face, our method takes two images as input, i.e., one in its original style and the other in the aggregated style. In experiments, we observe that the large variance of image styles would degenerate the performance of facial landmark detectors. Moreover, we show the robustness of our method to the large variance of image styles by comparing to a variant of our approach, in which the generative adversarial module is removed, and no style-aggregated images are used. Our approach is demonstrated to perform well when compared with state-of-the-art algorithms on benchmark datasets AFLW and 300-W. Code is publicly available on GitHub: https://github.com/D-X-Y/SAN

show abstract

“…Disentangled representation [22,70] is a straightforward idea to decouple the speaker identity features from the identity unrelated ones. Recently, disentangled representation has been explored in various computer vision applications, e.g., exposing invariant features for face recognition [62] and person re-identification [9], attribute transfer via adversarial disentanglement [30,37]. In the audio domain, seminal works [2,42,63,72] focus on robust identity representation by reducing the environmental complexity through adversarial learning.…”

Section: Introductionmentioning

confidence: 99%