via c# based native iOS development and quick connection to Bluemix with IBM MobileFirst SDK for Xamarin part 3.
In the previous blog post I connected to MobileFirst platform (MFP) and accessed the data from RSS feed from CNN through the MFP adapter in C# code for iOS.
In meantime I participated in the several conferences and meetups to demonstrate how quickly one could create a mobile app these days. The most notable ones were dedicated to Mobile “Women” Bootcamps in San Francisco, Los Angeles as well as “Women” reBoot in Redwood City. It is awesome to see growing interest in mobile technology everywhere.
In this paper we study the application of convolutional neural networks for jointly detecting objects depicted in still images and estimating their 3D pose. We identify different feature representations of oriented objects, and energies that lead a network to learn this representations. The choice of the representation is crucial since the pose of an object has a natural, continuous structure while its category is a discrete variable. We evaluate the different approaches on the joint object detection and pose estimation task of the Pascal3D+ benchmark using Average Viewpoint Precision. We show that a classification approach on discretized viewpoints achieves state-of-the-art performance for joint object detection and pose estimation, and significantly outperforms existing baselines on this benchmark.
We propose a simple two-step approach for speeding up convolution layers within large convolutional neural networks based on tensor decomposition and discriminative fine-tuning. Given a layer, we use non-linear least squares to compute a low-rank CP-decomposition of the 4D convolution kernel tensor into a sum of a small number of rank-one tensors. At the second step, this decomposition is used to replace the original convolutional layer with a sequence of four convolutional layers with small kernels. After such replacement, the entire network is fine-tuned on the training data using standard backpropagation process.
We evaluate this approach on two CNNs and show that it yields larger CPU speedups at the cost of lower accuracy drops compared to previous approaches. For the 36-class character classification CNN, our approach obtains a 8.5x CPU speedup of the whole network with only minor accuracy drop (1% from 91% to 90%). For the standard ImageNet architecture (AlexNet), the approach speeds up the second convolution layer by a factor of 4x at the cost of 1% increase of the overall top-5 classification error.