ARoFace: Alignment Robustness to Improve Low-Quality Face Recognition

• URL: http://arxiv.org/abs/2407.14972v1
• Date: Sat, 20 Jul 2024 19:58:41 GMT
• Title: ARoFace: Alignment Robustness to Improve Low-Quality Face Recognition
• Authors: Mohammad Saeed Ebrahimi Saadabadi, Sahar Rahimi Malakshan, Ali Dabouei, Nasser M. Nasrabadi,
• Abstract summary: We propose a method that considers Face Alignment Errors (FAE) as another quality factor that is tailored to Face Recognition (FR) We formalize the problem as a combination of differentiable spatial transformations and adversarial data augmentation in FR. We demonstrate the benefits of the proposed method by conducting evaluations on IJB-B, IJB-C, IJB-S and TinyFace.
• Score: 16.40653529334528
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Aiming to enhance Face Recognition (FR) on Low-Quality (LQ) inputs, recent studies suggest incorporating synthetic LQ samples into training. Although promising, the quality factors that are considered in these works are general rather than FR-specific, \eg, atmospheric turbulence, resolution, \etc. Motivated by the observation of the vulnerability of current FR models to even small Face Alignment Errors (FAE) in LQ images, we present a simple yet effective method that considers FAE as another quality factor that is tailored to FR. We seek to improve LQ FR by enhancing FR models' robustness to FAE. To this aim, we formalize the problem as a combination of differentiable spatial transformations and adversarial data augmentation in FR. We perturb the alignment of the training samples using a controllable spatial transformation and enrich the training with samples expressing FAE. We demonstrate the benefits of the proposed method by conducting evaluations on IJB-B, IJB-C, IJB-S (+4.3\% Rank1), and TinyFace (+2.63\%). \href{https://github.com/msed-Ebrahimi/ARoFace}{https://github.com/msed-Ebrahimi/ARoFace}

Related papers

• Adversarial Attacks on Both Face Recognition and Face Anti-spoofing Models [47.72177312801278]
  Adrial attacks on Face Recognition (FR) systems have proven highly effective in compromising pure FR models. We propose a novel setting of adversarially attacking both FR and Face Anti-Spoofing (FAS) models simultaneously. We introduce a new attack method, namely Style-aligned Distribution Biasing (SDB), to improve the capacity of black-box attacks on both FR and FAS models.
  arXiv  Detail & Related papers  (2024-05-27T08:30:29Z)
• GraFIQs: Face Image Quality Assessment Using Gradient Magnitudes [9.170455788675836]
  Face Image Quality Assessment (FIQA) estimates the utility of face images for automated face recognition (FR) systems. We propose in this work a novel approach to assess the quality of face images based on inspecting the required changes in the pre-trained FR model weights.
  arXiv  Detail & Related papers  (2024-04-18T14:07:08Z)
• CATFace: Cross-Attribute-Guided Transformer with Self-Attention Distillation for Low-Quality Face Recognition [12.129404936688752]
  We propose a novel multi-branch neural network that leverages soft biometric (SB) attribute information to boost the performance of face recognition (FR) We introduce a novel self-attention distillation framework that effectively highlights crucial facial regions, such as landmarks by aligning low-quality images with those of their high-quality counterparts in the feature space.
  arXiv  Detail & Related papers  (2024-01-05T19:21:31Z)
• CATfOOD: Counterfactual Augmented Training for Improving Out-of-Domain Performance and Calibration [59.48235003469116]
  We show that data augmentation consistently enhances OOD performance. We also show that CF augmented models which are easier to calibrate also exhibit much lower entropy when assigning importance.
  arXiv  Detail & Related papers  (2023-09-14T16:16:40Z)
• 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)
• A Quality Aware Sample-to-Sample Comparison for Face Recognition [13.96448286983864]
  This work integrates a quality-aware learning process at the sample level into the classification training paradigm (QAFace) Our method adaptively finds and assigns more attention to the recognizable low-quality samples in the training datasets.
  arXiv  Detail & Related papers  (2023-06-06T20:28:04Z)
• Blind Face Restoration: Benchmark Datasets and a Baseline Model [63.053331687284064]
  Blind Face Restoration (BFR) aims to construct a high-quality (HQ) face image from its corresponding low-quality (LQ) input. We first synthesize two blind face restoration benchmark datasets called EDFace-Celeb-1M (BFR128) and EDFace-Celeb-150K (BFR512) State-of-the-art methods are benchmarked on them under five settings including blur, noise, low resolution, JPEG compression artifacts, and the combination of them (full degradation)
  arXiv  Detail & Related papers  (2022-06-08T06:34:24Z)
• AdaFace: Quality Adaptive Margin for Face Recognition [56.99208144386127]
  We introduce another aspect of adaptiveness in the loss function, namely the image quality. We propose a new loss function that emphasizes samples of different difficulties based on their image quality. Our method, AdaFace, improves the face recognition performance over the state-of-the-art (SoTA) on four datasets.
  arXiv  Detail & Related papers  (2022-04-03T01:23:41Z)
• Learning Transformer Features for Image Quality Assessment [53.51379676690971]
  We propose a unified IQA framework that utilizes CNN backbone and transformer encoder to extract features. The proposed framework is compatible with both FR and NR modes and allows for a joint training scheme.
  arXiv  Detail & Related papers  (2021-12-01T13:23:00Z)
• Feature Quantization Improves GAN Training [126.02828112121874]
  Feature Quantization (FQ) for the discriminator embeds both true and fake data samples into a shared discrete space. Our method can be easily plugged into existing GAN models, with little computational overhead in training.
  arXiv  Detail & Related papers  (2020-04-05T04:06:50Z)

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.