Triplet probabilistic embedding for face verification and clustering

@article{Sankaranarayanan2016TripletPE,
  title={Triplet probabilistic embedding for face verification and clustering},
  author={Swami Sankaranarayanan and Azadeh Alavi and Carlos Domingo Castillo and Rama Chellappa},
  journal={2016 IEEE 8th International Conference on Biometrics Theory, Applications and Systems (BTAS)},
  year={2016},
  pages={1-8}
}
  • S. Sankaranarayanan, A. Alavi, +1 author R. Chellappa
  • Published 19 April 2016
  • Computer Science, Mathematics
  • 2016 IEEE 8th International Conference on Biometrics Theory, Applications and Systems (BTAS)
Despite significant progress made over the past twenty five years, unconstrained face verification remains a challenging problem. This paper proposes an approach that couples a deep CNN-based approach with a low-dimensional discriminative embedding step, learned using triplet probability constraints to address the unconstrained face verification problem. Aside from yielding performance improvements, this embedding provides significant advantages in terms of memory and for post-processing… 
Deep Transfer Network for Unconstrained Face Verification
TLDR
The Deep Transfer Network (DTN) is proposed which integrates transfer learning and attention-based feature aggregation mechanism together and can produce results comparable to the state-of-the-art in the challenging face dataset, IJB-A.
L2-constrained Softmax Loss for Discriminative Face Verification
TLDR
This paper adds an L2-constraint to the feature descriptors which restricts them to lie on a hypersphere of a fixed radius and shows that integrating this simple step in the training pipeline significantly boosts the performance of face verification.
Crystal Loss and Quality Pooling for Unconstrained Face Verification and Recognition
TLDR
This paper proposes a new loss function, called Crystal Loss, that restricts the features to lie on a hypersphere of a fixed radius and shows that integrating this simple step in the training pipeline significantly improves the performance of face verification and recognition systems.
Unconstrained Still/Video-Based Face Verification with Deep Convolutional Neural Networks
TLDR
The design details of a deep learning system for unconstrained face recognition, including modules for face detection, association, alignment and face verification are presented and some open issues regarding DCNNs for face verification problems are discussed.
Deep representation for partially occluded face verification
TLDR
A novel convolutional neural network which was designed specifically for the verification between the occluded and non-occluded faces for the same identity is proposed.
Hybrid Siamese Network for Unconstrained Face Verification and Clustering under Limited Resources
TLDR
An unconstrained face verification approach that is dependent on Hybrid Siamese architecture under limited resources and achieves near-human accuracy on the Labeled Faces in the Wild benchmark, which is competitive with other techniques that are presented in the literature.
A Good Practice Towards Top Performance of Face Recognition: Transferred Deep Feature Fusion
TLDR
This paper proposes a unified learning framework named Transferred Deep Feature Fusion (TDFF) targeting at the new IARPA Janus Benchmark A (IJB-A) face recognition dataset released by NIST face challenge, and exhibits excellent performance on IJB-A dataset.
Enhancing Convolutional Neural Networks for Face Recognition with Occlusion Maps and Batch Triplet Loss
TLDR
A simple method to find out which parts of the human face are more important to achieve a high recognition rate, and use that information during training to force a convolutional neural network to learn discriminative features from all the face regions more equally, including those that typical approaches tend to pay less attention to is proposed.
Reconstruction-Based Disentanglement for Pose-Invariant Face Recognition
TLDR
This paper presents a method for learning a feature representation that is invariant to pose, without requiring extensive pose coverage in training data, and proposes a new feature reconstruction metric learning to explicitly disentangle identity and pose.
Pose-Robust Face Verification by Exploiting Competing Tasks
TLDR
This paper learns a joint model for these two tasks and explicitly discourage the information sharing between pose and identity verification metrics so as to mitigate the information contained in the pose verification task leading to making the identity metrics for face verification more pose-robust.
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 31 REFERENCES
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.
FaceNet: A unified embedding for face recognition and clustering
TLDR
A system that directly learns a mapping from face images to a compact Euclidean space where distances directly correspond to a measure offace similarity, and achieves state-of-the-art face recognition performance using only 128-bytes perface.
Unconstrained face verification using deep CNN features
TLDR
An algorithm for unconstrained face verification based on deep convolutional features and evaluate it on the newly released IARPA Janus Benchmark A (IJB-A) dataset as well as on the traditional Labeled Face in the Wild (LFW) dataset.
Learning Face Representation from Scratch
TLDR
A semi-automatical way to collect face images from Internet is proposed and a large scale dataset containing about 10,000 subjects and 500,000 images, called CASIAWebFace is built, based on which a 11-layer CNN is used to learn discriminative representation and obtain state-of-theart accuracy on LFW and YTF.
Fisher Vector Faces in the Wild
TLDR
This paper shows that Fisher vectors on densely sampled SIFT features are capable of achieving state-of-the-art face verification performance on the challenging “Labeled Faces in the Wild” benchmark, and shows that a compact descriptor can be learnt from them using discriminative metric learning.
Pushing the frontiers of unconstrained face detection and recognition: IARPA Janus Benchmark A
TLDR
Baseline accuracies for both face detection and face recognition from commercial and open source algorithms demonstrate the challenge offered by this new unconstrained benchmark.
Deep Face Recognition
TLDR
It is shown how a very large scale dataset can be assembled by a combination of automation and human in the loop, and the trade off between data purity and time is discussed.
Face Search at Scale: 80 Million Gallery
TLDR
A face search system which combines a fast search procedure, coupled with a state-of-the-art commercial off the shelf (COTS) matcher, in a cascaded framework that offers an excellent trade-off between accuracy and scalability on datasets consisting of millions of images.
Frontal to profile face verification in the wild
TLDR
The aim of this data set is to isolate the factor of pose variation in terms of extreme poses like profile, where many features are occluded, along with other `in the wild' variations to suggest that there is a gap between human performance and automatic face recognition methods for large pose variations in unconstrained images.
Toward Large-Population Face Identification in Unconstrained Videos
TLDR
A sparsity-induced scalable optimization method is presented, which solves the large-scale MTJSR problem by sequentially solving a series of smaller-scale subproblems with theoretically guaranteed convergency.
...
1
2
3
4
...