Low-Cost Transfer Learning of Face Tasks
arXiv:1901.02675
Abstract
Do we know what the different filters of a face network represent? Can we use this filter information to train other tasks without transfer learning? For instance, can age, head pose, emotion and other face related tasks be learned from face recognition network without transfer learning? Understanding the role of these filters allows us to transfer knowledge across tasks and take advantage of large data sets in related tasks. Given a pretrained network, we can infer which tasks the network generalizes for and the best way to transfer the information to a new task.
References in corpus (10)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Intriguing properties of neural networks
- DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
- How transferable are features in deep neural networks?
- Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks
- Object Detectors Emerge in Deep Scene CNNs
- SVCCA: Singular Vector Canonical Correlation Analysis for Deep Learning Dynamics and Interpretability
- Multifaceted Feature Visualization: Uncovering the Different Types of Features Learned By Each Neuron in Deep Neural Networks
- Do Convnets Learn Correspondence?
- Understanding Intra-Class Knowledge Inside CNN