OTFace: Hard Samples Guided Optimal Transport Loss for Deep Face Representation

• URL: http://arxiv.org/abs/2203.14461v1
• Date: Mon, 28 Mar 2022 02:57:04 GMT
• Title: OTFace: Hard Samples Guided Optimal Transport Loss for Deep Face Representation
• Authors: Jianjun Qian, Shumin Zhu, Chaoyu Zhao, Jian Yang and Wai Keung Wong
• Abstract summary: Face representation in the wild is extremely hard due to the large scale face variations. This paper proposes the hard samples guided optimal transport (OT) loss for deep face representation, OTFace.
• Score: 31.220594076407444
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Face representation in the wild is extremely hard due to the large scale face variations. To this end, some deep convolutional neural networks (CNNs) have been developed to learn discriminative feature by designing properly margin-based losses, which perform well on easy samples but fail on hard samples. Based on this, some methods mainly adjust the weights of hard samples in training stage to improve the feature discrimination. However, these methods overlook the feature distribution property which may lead to better results since the miss-classified hard samples may be corrected by using the distribution metric. This paper proposes the hard samples guided optimal transport (OT) loss for deep face representation, OTFace for short. OTFace aims to enhance the performance of hard samples by introducing the feature distribution discrepancy while maintain the performance on easy samples. Specifically, we embrace triplet scheme to indicate hard sample groups in one mini-batch during training. OT is then used to characterize the distribution differences of features from the high level convolutional layer. Finally, we integrate the margin-based-softmax (e.g. ArcFace or AM-Softmax) and OT to guide deep CNN learning. Extensive experiments are conducted on several benchmark databases. The quantitative results demonstrate the advantages of the proposed OTFace over state-of-the-art methods.

Related papers

• Deep Boosting Multi-Modal Ensemble Face Recognition with Sample-Level Weighting [11.39204323420108]
  Deep convolutional neural networks have achieved remarkable success in face recognition. The current training benchmarks exhibit an imbalanced quality distribution. This poses issues for generalization on hard samples since they are underrepresented during training. Inspired by the well-known AdaBoost, we propose a sample-level weighting approach to incorporate the importance of different samples into the FR loss.
  arXiv  Detail & Related papers  (2023-08-18T01:44:54Z)
• Learning Compact Features via In-Training Representation Alignment [19.273120635948363]
  In each epoch, the true gradient of the loss function is estimated using a mini-batch sampled from the training set. We propose In-Training Representation Alignment (ITRA) that explicitly aligns feature distributions of two different mini-batches with a matching loss. We also provide a rigorous analysis of the desirable effects of the matching loss on feature representation learning.
  arXiv  Detail & Related papers  (2022-11-23T22:23:22Z)
• ScoreMix: A Scalable Augmentation Strategy for Training GANs with Limited Data [93.06336507035486]
  Generative Adversarial Networks (GANs) typically suffer from overfitting when limited training data is available. We present ScoreMix, a novel and scalable data augmentation approach for various image synthesis tasks.
  arXiv  Detail & Related papers  (2022-10-27T02:55:15Z)
• Saliency Grafting: Innocuous Attribution-Guided Mixup with Calibrated Label Mixing [104.630875328668]
  Mixup scheme suggests mixing a pair of samples to create an augmented training sample. We present a novel, yet simple Mixup-variant that captures the best of both worlds.
  arXiv  Detail & Related papers  (2021-12-16T11:27:48Z)
• Sample and Computation Redistribution for Efficient Face Detection [137.19388513633484]
  Training data sampling and computation distribution strategies are the keys to efficient and accurate face detection. scrfdf34 outperforms the best competitor, TinaFace, by $3.86%$ (AP at hard set) while being more than emph3$times$ faster on GPUs with VGA-resolution images.
  arXiv  Detail & Related papers  (2021-05-10T23:51:14Z)
• Jo-SRC: A Contrastive Approach for Combating Noisy Labels [58.867237220886885]
  We propose a noise-robust approach named Jo-SRC (Joint Sample Selection and Model Regularization based on Consistency) Specifically, we train the network in a contrastive learning manner. Predictions from two different views of each sample are used to estimate its "likelihood" of being clean or out-of-distribution.
  arXiv  Detail & Related papers  (2021-03-24T07:26:07Z)
• Exploring Adversarial Robustness of Deep Metric Learning [25.12224002984514]
  DML uses deep neural architectures to learn semantic embeddings of the input. We tackle the primary challenge of the metric losses being dependent on the samples in a mini-batch. Using experiments on three commonly-used DML datasets, we demonstrate 5-76 fold increases in adversarial accuracy.
  arXiv  Detail & Related papers  (2021-02-14T23:18:12Z)
• Robust Visual Tracking via Statistical Positive Sample Generation and Gradient Aware Learning [28.60114425270413]
  CNN based trackers have achieved state-of-the-art performance on multiple benchmark datasets. We propose a robust tracking method via Statistical Positive sample generation and Gradient Aware learning (SPGA) We show that the proposed SPGA performs favorably against several state-of-the-art trackers.
  arXiv  Detail & Related papers  (2020-11-09T09:14:58Z)
• Multi-Scale Positive Sample Refinement for Few-Shot Object Detection [61.60255654558682]
  Few-shot object detection (FSOD) helps detectors adapt to unseen classes with few training instances. We propose a Multi-scale Positive Sample Refinement (MPSR) approach to enrich object scales in FSOD. MPSR generates multi-scale positive samples as object pyramids and refines the prediction at various scales.
  arXiv  Detail & Related papers  (2020-07-18T09:48:29Z)
• Improving Face Recognition from Hard Samples via Distribution Distillation Loss [131.61036519863856]
  Large facial variations are the main challenge in face recognition. We propose a novel Distribution Distillation Loss to narrow the performance gap between easy and hard samples. We have conducted extensive experiments on both generic large-scale face benchmarks and benchmarks with diverse variations on race, resolution and pose.
  arXiv  Detail & Related papers  (2020-02-10T11:25:22Z)

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.