Exploring Complementarity and Explainability in CNNs for Periocular Verification Across Acquisition Distances
We study the complementarity of different CNNs for periocular verification at different distances on the UBIPr database. We train three architectures of increasing complexity (SqueezeNet, MobileNetv2, and ResNet50) on a large set of eye crops from VGGFace2. We analyse performance with cosine and chi2 metrics, compare different network initialisations, and apply score-level fusion via logistic regression. In addition, we use LIME heatmaps and Jensen-Shannon divergence to compare attention patterns of the CNNs. While ResNet50 consistently performs best individually, the fusion provides substantial gains, especially when combining all three networks. Heatmaps show that networks usually focus on distinct regions of a given image, which explains their complementarity. Our method significantly outperforms previous works on UBIPr, achieving a new state-of-the-art.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Explicit Over Implicit: Enhancing CNNs Via Complex Structure Tensor Representations for Periocular Recognition
Our study provides evidence that CNNs struggle to extract orientation features effectively. We show that using the Complex Structure Tensor, which contains compact orientation features with certainties, as input to CNNs …
Understanding and Improving CNNs with Complex Structure Tensor: A Biometrics Study
Our study provides evidence that CNNs struggle to effectively extract orientation features. We show that the use of Complex Structure Tensor, which contains compact orientation features with certainties, as input to CNNs…
Improving Makeup Face Verification by Exploring Part-Based Representations
Recently, we have seen an increase in the global facial recognition market size. Despite significant advances in face recognition technology with the adoption of convolutional neural networks, there are still open challe…
Face RecognitionFace VerificationOne-Shot Learning for Periocular Recognition: Exploring the Effect of Domain Adaptation and Data Bias on Deep Representations
One weakness of machine-learning algorithms is the need to train the models for a new task. This presents a specific challenge for biometric recognition due to the dynamic nature of databases and, in some instances, the …
Domain AdaptationOne-Shot LearningPeriocular Embedding Learning with Consistent Knowledge Distillation from Face
Periocular biometric, the peripheral area of the ocular, is a collaborative alternative to the face, especially when the face is occluded or masked. However, in practice, sole periocular biometric capture the least salie…
Knowledge DistillationPrediction