Deep Learning Face Attributes in the Wild

@article{Liu2015DeepLF,
  title={Deep Learning Face Attributes in the Wild},
  author={Ziwei Liu and Ping Luo and Xiaogang Wang and Xiaoou Tang},
  journal={2015 IEEE International Conference on Computer Vision (ICCV)},
  year={2015},
  pages={3730-3738}
}
  • Ziwei Liu, Ping Luo, Xiaoou Tang
  • Published 27 November 2014
  • Computer Science
  • 2015 IEEE International Conference on Computer Vision (ICCV)
Predicting face attributes in the wild is challenging due to complex face variations. [] Key Result (3) It also demonstrates that the high-level hidden neurons of ANet automatically discover semantic concepts after pre-training with massive face identities, and such concepts are significantly enriched after fine-tuning with attribute tags. Each attribute can be well explained with a sparse linear combination of these concepts.

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

TLDR
This paper employs off-the-shelf CNNs trained for face recognition tasks to do facial feature extraction, combined with conventional face localization techniques, and suggests two potentially important questions in using CNNs for face attribute prediction: how to maximally leverage the power of CNN representations and how to best combine traditional computer vision techniques with deep learning networks.

Face Attribute Prediction with classification CNN

TLDR
This paper considers the mid-level CNN features as an alternative to the high-level ones for attribute prediction, based on the observation that face attributes are different: some of them are locally oriented while others are globally defined.

Face attribute prediction using off-the-shelf CNN features

TLDR
This paper combines with conventional face localization techniques, and uses off-the-shelf architectures trained for face recognition to build facial descriptors, demonstrating an efficient face attribute prediction approach and raising an important question: how to leverage the power of off- the- shelf CNN representations for novel tasks.

Face Attributes Recognition via Deep Multi-Task Cascade

TLDR
A deep multi-task cascaded network for face attributes recognition is proposed, which is trained in an end-to-end way by the combination of attribute-associated region discovery and attribute prediction together.

Leveraging mid-level deep representations for predicting face attributes in the wild

TLDR
The investigations reveal that the mid-level deep representations outperform the prediction accuracy achieved by the (fine-tuned) high-level abstractions and achieve state-of-the-art prediction performance on CelebA and LFWA datasets.

General-to-specific learning for facial attribute classification in the wild

Fine-Grained Face Annotation Using Deep Multi-Task CNN

TLDR
A multi-task learning-based convolutional neural network (MTL-CNN) able to estimate multiple tags describing face images simultaneously and taking into account the correlation among face attributes is presented.

Robust RGB-D Face Recognition Using Attribute-Aware Loss

TLDR
A new CNN-based face recognition approach that incorporates such attributes into the training process using an attribute-aware loss function that regularizes the feature mapping using attribute proximity, which greatly improve the accuracy and robustness of face recognition.

Transferring from face recognition to face attribute prediction through adaptive selection of off-the-shelf CNN representations

TLDR
This paper addresses the problem of transferring CNNs pre-trained for face recognition to a face attribute prediction task by selecting face descriptors from off-the-shelf hierarchical CNN representations for recognizing different attributes through an adaptive representation selection.

A Deep Cascade Network for Unaligned Face Attribute Classification

TLDR
A cascade network that simultaneously learns to localize face regions specific to attributes and performs attribute classification without alignment is proposed, achieving significantly better performance than state-of-the-art methods on unaligned CelebA dataset.
...

References

SHOWING 1-10 OF 45 REFERENCES

Deep Attribute Networks

TLDR
The potential of deep learning for attribute-based classification is demonstrated by showing comparable results with existing state-of-the-art results and does away with calculating low-level features which are maybe unreliable and computationally expensive.

DeepFace: Closing the Gap to Human-Level Performance in Face Verification

TLDR
This work revisits both the alignment step and the representation step by employing explicit 3D face modeling in order to apply a piecewise affine transformation, and derive a face representation from a nine-layer deep neural network.

PANDA: Pose Aligned Networks for Deep Attribute Modeling

TLDR
A new method which combines part-based models and deep learning by training pose-normalized CNNs for inferring human attributes from images of people under large variation of viewpoint, pose, appearance, articulation and occlusion is proposed.

Deep Learning Face Representation by Joint Identification-Verification

TLDR
This paper shows that the face identification-verification task can be well solved with deep learning and using both face identification and verification signals as supervision, and the error rate has been significantly reduced.

A Deep Sum-Product Architecture for Robust Facial Attributes Analysis

TLDR
This work has modeled region interdependencies with a discriminative decision tree, where each node consists of a detector and a classifier trained on a local region, which makes it more robust to occlusions and misdetection of face regions.

Hierarchical face parsing via deep learning

TLDR
A novel face parser is proposed, which recasts segmentation of face components as a cross-modality data transformation problem, i.e., transforming an image patch to a label map.

Multi-View Perceptron: a Deep Model for Learning Face Identity and View Representations

TLDR
This paper proposes a novel deep neural net, named multi-view perceptron (MVP), which can untangle the identity and view features, and in the meanwhile infer a full spectrum of multi- view images, given a single 2D face image.

Aggregate channel features for multi-view face detection

TLDR
Following the learning pipelines in Viola-Jones framework, the multi-view face detector using aggregate channel features shows competitive performance against state-of-the-art algorithms on AFW and FDDB test-sets, while runs at 42 FPS on VGA images.

Deep Convolutional Network Cascade for Facial Point Detection

TLDR
The proposed approach outperforms state-of-the-art methods in both detection accuracy and reliability and can avoid local minimum caused by ambiguity and data corruption in difficult image samples due to occlusions, large pose variations, and extreme lightings.

Attribute and simile classifiers for face verification

TLDR
Two novel methods for face verification using binary classifiers trained to recognize the presence or absence of describable aspects of visual appearance and a new data set of real-world images of public figures acquired from the internet.