Hard-Mining Loss based Convolutional Neural Network for Face Recognition

  title={Hard-Mining Loss based Convolutional Neural Network for Face Recognition},
  author={Yash Srivastava and Vaishnav Murali and Shiv Ram Dubey},
Face Recognition is one of the prominent problems in the computer vision domain. Witnessing advances in deep learning, significant work has been observed in face recognition, which touched upon various parts of the recognition framework like Convolutional Neural Network (CNN), Layers, Loss functions, etc. Various loss functions such as Cross-Entropy, Angular-Softmax and ArcFace have been introduced to learn the weights of network for face recognition. However, these loss functions are not able… Expand
PSNet: Parametric Sigmoid Norm Based CNN for Face Recognition
This paper proposes a PSNet CNN model by using the PSN layer, a Parametric Sigmoid Norm (PSN) layer just before the final fully-connected layer that forces the network to learn the visual features of difficult examples. Expand
On the Performance of Convolutional Neural Networks under High and Low Frequency Information
It is observed that the trained CNN fails to generalize over the high and low frequency images, and the stochastic filtering based data augmentation during training is proposed in order to make the CNN robust against high andLow frequency images. Expand
Color Channel Perturbation Attacks for Fooling Convolutional Neural Networks and A Defense Against Such Attacks
This paper discovers the color robustness problem of CNN by proposing a color channel perturbation (CCP) attack to fool the CNNs and proposes a primary defense mechanism to this problem by augmenting the training dataset with the proposed CCP attack. Expand
Joint Triplet Autoencoder for Histopathological Colon Cancer Nuclei Retrieval
The promising performance using the proposed JTANet model against the Autoencoder and Siamese models for colon cancer nuclei retrieval in histopathological images is observed. Expand
AC-CovidNet: Attention Guided Contrastive CNN for Recognition of Covid-19 in Chest X-Ray Images
Inspired by the limitations of the open-source work in this field, the proposed attention guided contrastive CNN architecture (AC-CovidNet) for Covid-19 detection in CXR images exhibits very promising performance as compared to the existing methods even with limited training data. Expand


A Performance Comparison of Loss Functions for Deep Face Recognition
A performance comparison of different loss functions such as Cross-Entropy, Angular Softmax, Additive-Margin Soft max, ArcFace and Marginal Loss for face recognition is presented. Expand
Minimum Margin Loss for Deep Face Recognition
Experimental results show that the proposed MML loss function has led to new state of the art in face recognition, reducing the negative effect of margin bias. Expand
Marginal Loss for Deep Face Recognition
A new supervision signal named marginal loss is proposed for deep face recognition that simultaneously minimises the intra-class variances as well as maximises the inter-class distances by focusing on the marginal samples. Expand
CosFace: Large Margin Cosine Loss for Deep Face Recognition
This paper reformulates the softmax loss as a cosine loss by L2 normalizing both features and weight vectors to remove radial variations, based on which acosine margin term is introduced to further maximize the decision margin in the angular space, and achieves minimum intra-class variance and maximum inter- class variance by virtue of normalization and cosine decision margin maximization. Expand
ArcFace: Additive Angular Margin Loss for Deep Face Recognition
This paper presents arguably the most extensive experimental evaluation against all recent state-of-the-art face recognition methods on ten face recognition benchmarks, and shows that ArcFace consistently outperforms the state of the art and can be easily implemented with negligible computational overhead. Expand
SphereFace: Deep Hypersphere Embedding for Face Recognition
This paper proposes the angular softmax (A-Softmax) loss that enables convolutional neural networks (CNNs) to learn angularly discriminative features in deep face recognition (FR) problem under open-set protocol. Expand
Learning Face Representation from Scratch
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. Expand
FaceNet: A unified embedding for face recognition and clustering
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. Expand
Deep Learning Face Representation by Joint Identification-Verification
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. Expand
AdaptiveFace: Adaptive Margin and Sampling for Face Recognition
  • H. Liu, Xiangyu Zhu, Zhen Lei, S. Li
  • Computer Science
  • 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2019
This paper proposes the Adaptive Margin Softmax to adjust the margins for different classes adaptively, and makes the sampling process adaptive in two folds: Firstly, the Hard Prototype Mining to adaptively select a small number of hard classes to participate in classification, and secondly, theAdaptive Data Sampling to find valuable samples for training adaptively. Expand