Towards Interpretable Face Recognition
arXiv:1805.00611
Abstract
Deep CNNs have been pushing the frontier of visual recognition over past years. Besides recognition accuracy, strong demands in understanding deep CNNs in the research community motivate developments of tools to dissect pre-trained models to visualize how they make predictions. Recent works further push the interpretability in the network learning stage to learn more meaningful representations. In this work, focusing on a specific area of visual recognition, we report our efforts towards interpretable face recognition. We propose a spatial activation diversity loss to learn more structured face representations. By leveraging the structure, we further design a feature activation diversity loss to push the interpretable representations to be discriminative and robust to occlusions. We demonstrate on three face recognition benchmarks that our proposed method is able to improve face recognition accuracy with easily interpretable face representations.
arXiv comment10 pages, 9 figures, 6 tables, To appear in ICCV 2019 as an oral paper
References in corpus (17)
- Show, Attend and Tell: Neural Image Caption Generation with Visual Attention
- Intriguing properties of neural networks
- Learning Face Representation from Scratch
- Focal Loss for Dense Object Detection
- InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets
- DenseNet: Implementing Efficient ConvNet Descriptor Pyramids
- Visualizing Deep Convolutional Neural Networks Using Natural Pre-Images
- Naive-Deep Face Recognition: Touching the Limit of LFW Benchmark or Not?
- Representation Learning by Rotating Your Faces
- On Learning 3D Face Morphable Model from In-the-wild Images
- Multicolumn Networks for Face Recognition
- Learning Deep Features via Congenerous Cosine Loss for Person Recognition
- Towards Large-Pose Face Frontalization in the Wild
- Neural Face Editing with Intrinsic Image Disentangling
- Nonlinear 3D Face Morphable Model
- Interpretable Convolutional Neural Networks
- Disentangling Features in 3D Face Shapes for Joint Face Reconstruction and Recognition