paper-with-me

홈 › Papers

NPT-Loss: A Metric Loss with Implicit Mining for Face Recognition

2021-03-05 · Syed Safwan Khalid, Muhammad Awais, Chi-Ho Chan, ZhenHua Feng, Ammarah Farooq, Ali Akbari, Josef Kittler

Face recognition (FR) using deep convolutional neural networks (DCNNs) has seen remarkable success in recent years. One key ingredient of DCNN-based FR is the appropriate design of a loss function that ensures discrimination between various identities. The state-of-the-art (SOTA) solutions utilise normalised Softmax loss with additive and/or multiplicative margins. Despite being popular, these Softmax+margin based losses are not theoretically motivated and the effectiveness of a margin is justified only intuitively. In this work, we utilise an alternative framework that offers a more direct mechanism of achieving discrimination among the features of various identities. We propose a novel loss that is equivalent to a triplet loss with proxies and an implicit mechanism of hard-negative mining. We give theoretical justification that minimising the proposed loss ensures a minimum separability between all identities. The proposed loss is simple to implement and does not require heavy hyper-parameter tuning as in the SOTA solutions. We give empirical evidence that despite its simplicity, the proposed loss consistently achieves SOTA performance in various benchmarks for both high-resolution and low-resolution FR tasks.

📄 PDF Abstract BibTeX arXiv:2103.03503

Code (0)

등록된 구현이 없습니다.

Tasks

Face RecognitionTriplet

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Triplet Loss The goal of Triplet loss, in the context of Siamese Networks, is to maximize the joint probability among all score-pairs i.e. the product of all probabilities. By using its…

Similar Papers 제목 키워드 기반

Hard-Mining Loss based Convolutional Neural Network for Face Recognition

2019-08-09 · Yash Srivastava, Vaishnav Murali, 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 recog…

Face Recognition

Depth-NeuS: Neural Implicit Surfaces Learning for Multi-view Reconstruction Based on Depth Information Optimization

2023-03-30 · Hanqi Jiang, Cheng Zeng, Runnan Chen, Shuai Liang 외

Recently, methods for neural surface representation and rendering, for example NeuS, have shown that learning neural implicit surfaces through volume rendering is becoming increasingly popular and making good progress. H…

Object ReconstructionSurface Reconstruction

Phase Transitions, Distance Functions, and Implicit Neural Representations

2021-06-14 · Yaron Lipman

Representing surfaces as zero level sets of neural networks recently emerged as a powerful modeling paradigm, named Implicit Neural Representations (INRs), serving numerous downstream applications in geometric deep learn…

Inductive BiasSurface Reconstruction

Margin Sample Mining Loss: A Deep Learning Based Method for Person Re-identification

2017-10-02 · Qiqi Xiao, Hao Luo, Chi Zhang

Person re-identification (ReID) is an important task in computer vision. Recently, deep learning with a metric learning loss has become a common framework for ReID. In this paper, we also propose a new metric learning lo…

Metric LearningPerson Re-IdentificationTriplet

Implicit Geometric Regularization for Learning Shapes

2020-02-24 · ICML 2020 1 · Amos Gropp, Lior Yariv, Niv Haim, Matan Atzmon 외

Representing shapes as level sets of neural networks has been recently proved to be useful for different shape analysis and reconstruction tasks. So far, such representations were computed using either: (i) pre-computed …