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

• URL: http://arxiv.org/abs/2103.03503v1
• Date: Fri, 5 Mar 2021 07:26:40 GMT
• Title: NPT-Loss: A Metric Loss with Implicit Mining for Face Recognition
• Authors: Syed Safwan Khalid, Muhammad Awais, Chi-Ho Chan, Zhenhua Feng, Ammarah Farooq, Ali Akbari and Josef Kittler
• Abstract summary: Face recognition 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. We propose a novel loss that is equivalent to a triplet loss with proxies and an implicit mechanism of hard-negative mining.
• Score: 28.773161837693344
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: 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.

Related papers

• EnsLoss: Stochastic Calibrated Loss Ensembles for Preventing Overfitting in Classification [1.3778851745408134]
  We propose a novel ensemble method, namely EnsLoss, to combine loss functions within the Empirical risk minimization framework. We first transform the CC conditions of losses into loss-derivatives, thereby bypassing the need for explicit loss functions. We theoretically establish the statistical consistency of our approach and provide insights into its benefits.
  arXiv  Detail & Related papers  (2024-09-02T02:40:42Z)
• A Universal Class of Sharpness-Aware Minimization Algorithms [57.29207151446387]
  We introduce a new class of sharpness measures, leading to new sharpness-aware objective functions. We prove that these measures are textitly expressive, allowing any function of the training loss Hessian matrix to be represented by appropriate hyper and determinants.
  arXiv  Detail & Related papers  (2024-06-06T01:52:09Z)
• Expressive Losses for Verified Robustness via Convex Combinations [67.54357965665676]
  We study the relationship between the over-approximation coefficient and performance profiles across different expressive losses. We show that, while expressivity is essential, better approximations of the worst-case loss are not necessarily linked to superior robustness-accuracy trade-offs.
  arXiv  Detail & Related papers  (2023-05-23T12:20:29Z)
• Stationary Point Losses for Robust Model [3.5651179772067465]
  Cross-entropy (CE) loss does not guarantee robust boundary for neural networks. We propose stationary point (SP) loss, which has at least one stationary point on the correct classification side. We demonstrate that robustness is improved under a variety of adversarial attacks by applying SP loss.
  arXiv  Detail & Related papers  (2023-02-19T13:39:19Z)
• Anti-Exploration by Random Network Distillation [63.04360288089277]
  We show that a naive choice of conditioning for the Random Network Distillation (RND) is not discriminative enough to be used as an uncertainty estimator. We show that this limitation can be avoided with conditioning based on Feature-wise Linear Modulation (FiLM) We evaluate it on the D4RL benchmark, showing that it is capable of achieving performance comparable to ensemble-based methods and outperforming ensemble-free approaches by a wide margin.
  arXiv  Detail & Related papers  (2023-01-31T13:18:33Z)
• Joint Discriminative and Metric Embedding Learning for Person Re-Identification [8.137833258504381]
  Person re-identification is a challenging task because of the high intra-class variance induced by the unrestricted nuisance factors of variations. Recent approaches postulate that powerful architectures have the capacity to learn feature representations invariant to nuisance factors.
  arXiv  Detail & Related papers  (2022-12-28T22:08:42Z)
• Learning Towards the Largest Margins [83.7763875464011]
  Loss function should promote the largest possible margins for both classes and samples. Not only does this principled framework offer new perspectives to understand and interpret existing margin-based losses, but it can guide the design of new tools.
  arXiv  Detail & Related papers  (2022-06-23T10:03:03Z)
• Label Distributionally Robust Losses for Multi-class Classification: Consistency, Robustness and Adaptivity [55.29408396918968]
  We study a family of loss functions named label-distributionally robust (LDR) losses for multi-class classification. Our contributions include both consistency and robustness by establishing top-$k$ consistency of LDR losses for multi-class classification. We propose a new adaptive LDR loss that automatically adapts the individualized temperature parameter to the noise degree of class label of each instance.
  arXiv  Detail & Related papers  (2021-12-30T00:27:30Z)
• Adaptive Weighted Discriminator for Training Generative Adversarial Networks [11.68198403603969]
  We introduce a new family of discriminator loss functions that adopts a weighted sum of real and fake parts. Our method can be potentially applied to any discriminator model with a loss that is a sum of the real and fake parts.
  arXiv  Detail & Related papers  (2020-12-05T23:55:42Z)
• Loss Function Search for Face Recognition [75.79325080027908]
  We develop a reward-guided search method to automatically obtain the best candidate. Experimental results on a variety of face recognition benchmarks have demonstrated the effectiveness of our method.
  arXiv  Detail & Related papers  (2020-07-10T03:40:10Z)
• A Feature-map Discriminant Perspective for Pruning Deep Neural Networks [24.062226363823257]
  We present a new mathematical formulation to accurately and efficiently quantify the feature-map discriminativeness. We analyze the theoretical property of DI, specifically the non-decreasing property, that makes DI a valid selection criterion. We propose a DI-based greedy pruning algorithm and structure distillation technique to automatically decide the pruned structure.
  arXiv  Detail & Related papers  (2020-05-28T06:25:22Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.