scispace - formally typeset
Proceedings ArticleDOI

A-LINK: Recognizing Disguised Faces via Active Learning based Inter-Domain Knowledge

01 Sep 2019-pp 1-8
TL;DR: This work proposes an active learning framework A-LINK*, that intelligently selects training samples from the target domain data, such that the decision boundary does not overfit to a particular set of variations, and better generalizes to encode variability.
Abstract: Recent advancements in deep learning have significantly increased the capabilities of face recognition. However, face recognition in an unconstrained environment is still an active research challenge. Covariates such as pose and low resolution have received significant attention, but “disguise” is considered an onerous covariate of face recognition. One primary reason for this is the unavailability of large and representative databases. To address the problem of recognizing disguised faces, we propose an active learning framework A-LINK*, that intelligently selects training samples from the target domain data, such that the decision boundary does not overfit to a particular set of variations, and better generalizes to encode variability. The framework further applies domain adaptation with the actively selected training samples to fine-tune the network. We demonstrate the effectiveness of the proposed framework on DFW and Multi-PIE datasets with state-of-the-art models such as LCSSE and DenseNet.
Topics: Active learning (machine learning) (54%), Facial recognition system (52%), Overfitting (51%), Deep learning (50%)
Citations
More filters

Proceedings ArticleDOI
01 Oct 2019-
Abstract: Mini-batch construction strategy is an important part of the deep representation learning. Different strategies have their advantages and limitations. Usually only one of them is selected to create mini-batches for training. However, in many cases their combination can be more efficient than using only one of them. In this paper, we propose Composite Mini-Batches - a technique to combine several mini-batch sampling strategies in one training process. The main idea is to compose mini-batches from several parts, and use different sampling strategy for each part. With this kind of mini-batch construction, we combine the advantages and reduce the limitations of the individual mini-batch sampling strategies. We also propose Interpolated Embeddings and Priority Class Sampling as complementary methods to improve the training of face representations. Our experiments on a challenging task of disguised face recognition confirm the advantages of the proposed methods.

2 citations


Cites background from "A-LINK: Recognizing Disguised Faces..."

  • ...In the worst case, these changes are made intentionally to hide ones identity or imitate the appearance of another person [15, 38, 47]....

    [...]


Journal ArticleDOI
01 Jun 2020-
TL;DR: Experimental results demonstrate the effectiveness and generalization of the proposed framework on the DFW and DFW2019 datasets with state-of-the-art deep learning featurization models such as LCSSE, ArcFace, and DenseNet.
Abstract: Face recognition in the unconstrained environment is an ongoing research challenge. Although several covariates of face recognition such as pose and low resolution have received significant attention, “disguise” is considered an onerous covariate of face recognition. One of the primary reasons for this is the scarcity of large and representative labeled databases, along with the lack of algorithms that work well for multiple covariates in such environments. In order to address the problem of face recognition in the presence of disguise, the paper proposes an active learning framework termed as A2-LINK. Starting with a face recognition machine-learning model, A2-LINK intelligently selects training samples from the target domain to be labeled and, using hybrid noises such as adversarial noise, fine-tunes a model that works well both in the presence and absence of disguise. Experimental results demonstrate the effectiveness and generalization of the proposed framework on the DFW and DFW2019 datasets with state-of-the-art deep learning featurization models such as LCSSE, ArcFace, and DenseNet.

Cites background or methods from "A-LINK: Recognizing Disguised Faces..."

  • ...Compared to A-LINK [28], an average absolute increase of 2....

    [...]

  • ...Models trained with A2-LINK even outperform A-LINK [28] by a significant margin, thus reinforcing...

    [...]

  • ...(A-LINK [28]) give a reasonably good increase in performance, both when dealing with disguise and multiresolution as covariates....

    [...]

  • ...2A shorter version of the manuscript was presented at IEEE International Conference on BTAS, 2019 [28]....

    [...]

  • ...This paper builds on top of A-LINK2 [28] and introduces an adversarial noise component while constructing hybrid noise inputs for the algorithm....

    [...]


References
More filters

Journal ArticleDOI
TL;DR: This final installment of the paper considers the case where the signals or the messages or both are continuously variable, in contrast with the discrete nature assumed until now.
Abstract: In this final installment of the paper we consider the case where the signals or the messages or both are continuously variable, in contrast with the discrete nature assumed until now. To a considerable extent the continuous case can be obtained through a limiting process from the discrete case by dividing the continuum of messages and signals into a large but finite number of small regions and calculating the various parameters involved on a discrete basis. As the size of the regions is decreased these parameters in general approach as limits the proper values for the continuous case. There are, however, a few new effects that appear and also a general change of emphasis in the direction of specialization of the general results to particular cases.

60,029 citations


Posted Content
Abstract: State-of-the-art object detection networks depend on region proposal algorithms to hypothesize object locations. Advances like SPPnet and Fast R-CNN have reduced the running time of these detection networks, exposing region proposal computation as a bottleneck. In this work, we introduce a Region Proposal Network (RPN) that shares full-image convolutional features with the detection network, thus enabling nearly cost-free region proposals. An RPN is a fully convolutional network that simultaneously predicts object bounds and objectness scores at each position. The RPN is trained end-to-end to generate high-quality region proposals, which are used by Fast R-CNN for detection. We further merge RPN and Fast R-CNN into a single network by sharing their convolutional features---using the recently popular terminology of neural networks with 'attention' mechanisms, the RPN component tells the unified network where to look. For the very deep VGG-16 model, our detection system has a frame rate of 5fps (including all steps) on a GPU, while achieving state-of-the-art object detection accuracy on PASCAL VOC 2007, 2012, and MS COCO datasets with only 300 proposals per image. In ILSVRC and COCO 2015 competitions, Faster R-CNN and RPN are the foundations of the 1st-place winning entries in several tracks. Code has been made publicly available.

23,121 citations


Proceedings ArticleDOI
21 Jul 2017-
Abstract: Recent work has shown that convolutional networks can be substantially deeper, more accurate, and efficient to train if they contain shorter connections between layers close to the input and those close to the output. In this paper, we embrace this observation and introduce the Dense Convolutional Network (DenseNet), which connects each layer to every other layer in a feed-forward fashion. Whereas traditional convolutional networks with L layers have L connections—one between each layer and its subsequent layer—our network has L(L+1)/2 direct connections. For each layer, the feature-maps of all preceding layers are used as inputs, and its own feature-maps are used as inputs into all subsequent layers. DenseNets have several compelling advantages: they alleviate the vanishing-gradient problem, strengthen feature propagation, encourage feature reuse, and substantially reduce the number of parameters. We evaluate our proposed architecture on four highly competitive object recognition benchmark tasks (CIFAR-10, CIFAR-100, SVHN, and ImageNet). DenseNets obtain significant improvements over the state-of-the-art on most of them, whilst requiring less memory and computation to achieve high performance. Code and pre-trained models are available at https://github.com/liuzhuang13/DenseNet.

15,769 citations


Proceedings Article
07 Dec 2015-
Abstract: State-of-the-art object detection networks depend on region proposal algorithms to hypothesize object locations. Advances like SPPnet [7] and Fast R-CNN [5] have reduced the running time of these detection networks, exposing region proposal computation as a bottleneck. In this work, we introduce a Region Proposal Network (RPN) that shares full-image convolutional features with the detection network, thus enabling nearly cost-free region proposals. An RPN is a fully-convolutional network that simultaneously predicts object bounds and objectness scores at each position. RPNs are trained end-to-end to generate high-quality region proposals, which are used by Fast R-CNN for detection. With a simple alternating optimization, RPN and Fast R-CNN can be trained to share convolutional features. For the very deep VGG-16 model [19], our detection system has a frame rate of 5fps (including all steps) on a GPU, while achieving state-of-the-art object detection accuracy on PASCAL VOC 2007 (73.2% mAP) and 2012 (70.4% mAP) using 300 proposals per image. Code is available at https://github.com/ShaoqingRen/faster_rcnn.

13,622 citations


Proceedings Article
21 Jun 2010-
TL;DR: Restricted Boltzmann machines were developed using binary stochastic hidden units that learn features that are better for object recognition on the NORB dataset and face verification on the Labeled Faces in the Wild dataset.
Abstract: Restricted Boltzmann machines were developed using binary stochastic hidden units. These can be generalized by replacing each binary unit by an infinite number of copies that all have the same weights but have progressively more negative biases. The learning and inference rules for these "Stepped Sigmoid Units" are unchanged. They can be approximated efficiently by noisy, rectified linear units. Compared with binary units, these units learn features that are better for object recognition on the NORB dataset and face verification on the Labeled Faces in the Wild dataset. Unlike binary units, rectified linear units preserve information about relative intensities as information travels through multiple layers of feature detectors.

12,455 citations


"A-LINK: Recognizing Disguised Faces..." refers methods in this paper

  • ...DFW: Architectures of modelsM1 andM2 are the same: it consists of an absolute difference layer over the two inputs (features extracted from images), followed by two layers with ReLU [16] activation of 512 and 64 neurons....

    [...]


Network Information
Performance
Metrics
No. of citations received by the Paper in previous years
YearCitations
20201
20191