mlsanityData to 7 Oct 2026

Analyzing the effectiveness of image augmentations for face recognition from limited data

arXiv 2105.08796 ↗First posted 18 May 2021cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

This work presents an analysis of the efficiency of image augmentations for the face recognition problem from limited data. We considered basic manipulations, generative methods, and their combinations for augmentations. Our results show that augmentations, in general, can considerably improve the quality of face recognition systems and the combination of generative and basic approaches performs better than the other tested techniques.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 15 of its 36 references that are in the map. First posted on arXiv 18 May 2021.

Builds on

15 of 36 references.

References · 15

  1. 2015FaceNet: A Unified Embedding for Face Recognition and Clusteringcited by 2,833
  2. 2017Random Erasing Data Augmentationcited by 1,235
  3. 2016MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognitioncited by 621
  4. 2017Regularizing Deep Neural Networks by Noise: Its Interpretation and Optimizationcited by 56
  5. 2019Semi-Supervised and Task-Driven Data Augmentationcited by 40
  6. 2015APAC: Augmented PAttern Classification with Neural Networkscited by 23
  7. 2019STaDA: Style Transfer as Data Augmentationcited by 21
  8. 2020Anomaly Detection based on Zero-Shot Outlier Synthesis and Hierarchical Feature Distillationcited by 18
  9. 2019Synthetic Augmentation and Feature-based Filtering for Improved Cervical Histopathology Image Classificationcited by 17
  10. 2017Data-Driven Color Augmentation Techniques for Deep Skin Image Analysiscited by 13
  11. 2020PA-GAN: Progressive Attention Generative Adversarial Network for Facial Attribute Editingcited by 13
  12. 2017Multi-label Class-imbalanced Action Recognition in Hockey Videos via 3D Convolutional Neural Networkscited by 12
3 more
  1. 2019Application of Low-resource Machine Translation Techniques to Russian-Tatar Language Paircited by 7
  2. 2019SART - Similarity, Analogies, and Relatedness for Tatar Language: New Benchmark Datasets for Word Embeddings Evaluationcited by 5
  3. 2018Data-specific Adaptive Threshold for Face Recognition and Authenticationcited by 2

Built on by

Not cited yet.