Learn More
Fine-grained recognition is challenging because the appearance variation within a category due to factors such as pose and viewpoint can be significantly higher than that across categories. We propose an architecture for fine-grained recognition that uses two separate feature extrac-tors based on convolutional neural networks to model the appearance due to(More)
The recent explosive growth in convolutional neural network (CNN) research has produced a variety of new archi-tectures for deep learning. One intriguing new architecture is the bilinear CNN (B-CNN), which has shown dramatic performance gains on certain fine-grained recognition problems [13]. We apply this new CNN to the challenging new face recognition(More)
  • 1