Dataset Augmentation for Pose and Lighting Invariant Face Recognition
The performance of modern face recognition systems is a function of the dataset on which they are trained. Most datasets are largely biased toward "near-frontal" views with benign lighting conditions, negatively effecting recognition performance on images that do not meet these criteria. The proposed approach demonstrates how a baseline training set can be augmented to increase pose and lighting variability using semi-synthetic images with simulated pose and lighting conditions. The semi-synthetic images are generated using a fast and robust 3-d shape estimation and rendering pipeline which includes the full head and background. Various methods of incorporating the semi-synthetic renderings into the training procedure of a state of the art deep neural network-based recognition system without modifying the structure of the network itself are investigated. Quantitative results are presented on the challenging IJB-A identification dataset using a state of the art recognition pipeline as a baseline.
Code (0)
등록된 구현이 없습니다.
Tasks
Face RecognitionSimilar Papers 제목 키워드 기반
Controllable Data Augmentation Through Deep Relighting
At the heart of the success of deep learning is the quality of the data. Through data augmentation, one can train models with better generalization capabilities and thus achieve greater results in their field of interest…
Data AugmentationDecoderClass-Invariant Test-Time Augmentation for Domain Generalization
Deep models often suffer significant performance degradation under distribution shifts. Domain generalization (DG) seeks to mitigate this challenge by enabling models to generalize to unseen domains. Most prior approache…
Domain GeneralizationTest-time AdaptationA data augmentation methodology for training machine/deep learning gait recognition algorithms
There are several confounding factors that can reduce the accuracy of gait recognition systems. These factors can reduce the distinctiveness, or alter the features used to characterise gait, they include variations in cl…
Data AugmentationGait RecognitionA Lighting-Invariant Point Processor for Shading
Under the conventional diffuse shading model with unknown directional lighting, the set of quadratic surface shapes that are consistent with the spatial derivatives of intensity at a single image point is a two-dimension…
Riemannian Geometry-Preserving Variational Autoencoder for MI-BCI Data Augmentation
This paper addresses the challenge of generating synthetic electroencephalogram (EEG) covariance matrices for motor imagery brain-computer interface (MI-BCI) applications. Objective: We aim to develop a generative model …
Data Augmentation