AdaFace: Quality Adaptive Margin for Face Recognition

• URL: http://arxiv.org/abs/2204.00964v1
• Date: Sun, 3 Apr 2022 01:23:41 GMT
• Title: AdaFace: Quality Adaptive Margin for Face Recognition
• Authors: Minchul Kim, Anil K. Jain, Xiaoming Liu
• Abstract summary: 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.
• Score: 56.99208144386127
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recognition in low quality face datasets is challenging because facial attributes are obscured and degraded. Advances in margin-based loss functions have resulted in enhanced discriminability of faces in the embedding space. Further, previous studies have studied the effect of adaptive losses to assign more importance to misclassified (hard) examples. In this work, we introduce another aspect of adaptiveness in the loss function, namely the image quality. We argue that the strategy to emphasize misclassified samples should be adjusted according to their image quality. Specifically, the relative importance of easy or hard samples should be based on the sample's image quality. We propose a new loss function that emphasizes samples of different difficulties based on their image quality. Our method achieves this in the form of an adaptive margin function by approximating the image quality with feature norms. Extensive experiments show that our method, AdaFace, improves the face recognition performance over the state-of-the-art (SoTA) on four datasets (IJB-B, IJB-C, IJB-S and TinyFace). Code and models are released in https://github.com/mk-minchul/AdaFace.

Related papers

• Impact of Face Alignment on Face Image Quality [0.0]
  The impact of alignment on face image quality has not been thoroughly investigated. Our study examines the impact of face alignment on face image quality scores.
  arXiv  Detail & Related papers  (2024-12-16T13:49:57Z)
• PETALface: Parameter Efficient Transfer Learning for Low-resolution Face Recognition [54.642714288448744]
  PETALface is the first work leveraging the powers of PEFT for low resolution face recognition. We introduce two low-rank adaptation modules to the backbone, with weights adjusted based on the input image quality to account for the difference in quality for the gallery and probe images. Experiments demonstrate that the proposed method outperforms full fine-tuning on low-resolution datasets while preserving performance on high-resolution and mixed-quality datasets.
  arXiv  Detail & Related papers  (2024-12-10T18:59:45Z)
• Rank-based No-reference Quality Assessment for Face Swapping [88.53827937914038]
  The metric of measuring the quality in most face swapping methods relies on several distances between the manipulated images and the source image. We present a novel no-reference image quality assessment (NR-IQA) method specifically designed for face swapping.
  arXiv  Detail & Related papers  (2024-06-04T01:36:29Z)
• Dual-Branch Network for Portrait Image Quality Assessment [76.27716058987251]
  We introduce a dual-branch network for portrait image quality assessment (PIQA) We utilize two backbone networks (textiti.e., Swin Transformer-B) to extract the quality-aware features from the entire portrait image and the facial image cropped from it. We leverage LIQE, an image scene classification and quality assessment model, to capture the quality-aware and scene-specific features as the auxiliary features.
  arXiv  Detail & Related papers  (2024-05-14T12:43:43Z)
• MetaF2N: Blind Image Super-Resolution by Learning Efficient Model Adaptation from Faces [51.42949911178461]
  We propose a method dubbed MetaF2N to fine-tune model parameters for adapting to the whole Natural image in a Meta-learning framework. Considering the gaps between the recovered faces and ground-truths, we deploy a MaskNet for adaptively predicting loss weights at different positions to reduce the impact of low-confidence areas.
  arXiv  Detail & Related papers  (2023-09-15T02:45:21Z)
• FaceQgen: Semi-Supervised Deep Learning for Face Image Quality Assessment [19.928262020265965]
  FaceQgen is a No-Reference Quality Assessment approach for face images. It generates a scalar quality measure related with the face recognition accuracy. It is trained from scratch using the SCface database.
  arXiv  Detail & Related papers  (2022-01-03T17:22:38Z)
• Cross-Quality LFW: A Database for Analyzing Cross-Resolution Image Face Recognition in Unconstrained Environments [8.368543987898732]
  Real-world face recognition applications often deal with suboptimal image quality or resolution due to different capturing conditions. Recent cross-resolution face recognition approaches used simple, arbitrary, and unrealistic down- and up-scaling techniques to measure distances against real-world edge-cases in image quality. We propose a new standardized benchmark dataset and evaluation protocol derived from the famous Labeled Faces in the Wild.
  arXiv  Detail & Related papers  (2021-08-23T17:04:32Z)
• Network Architecture Search for Face Enhancement [82.25775020564654]
  We present a multi-task face restoration network, called Network Architecture Search for Face Enhancement (NASFE) NASFE can enhance poor quality face images containing a single degradation (i.e. noise or blur) or multiple degradations (noise+blur+low-light)
  arXiv  Detail & Related papers  (2021-05-13T19:46:05Z)
• MagFace: A Universal Representation for Face Recognition and Quality Assessment [6.7044749347155035]
  This paper proposes MagFace, a category of losses that learn a universal feature embedding whose magnitude can measure the quality of the given face. Under the new loss, it can be proven that the magnitude of the feature embedding monotonically increases if the subject is more likely to be recognized. In addition, MagFace introduces an adaptive mechanism to learn a well within-class feature by pulling easy samples to class centers while pushing hard samples away.
  arXiv  Detail & Related papers  (2021-03-11T11:58:21Z)

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.