Deep Encoding

This is a CVPR 2017 submission Deep TEN: Texture Encoding Network. Here we share the idea of this paper briefly. We integrate the entire dictionary learning and encoding framework into a single CNN model. This model is compatible with existing deep learning framework and enables end-to-end material/texture recognition. We have achieved state-of-the-art results on several gold-standard benchmarks. As a side product, we obtain 49.8% relative improvement on STL-10 dataset comparing to previous state-of-the-art by joint training with CIFAR-10 dataset.

Read More


Torch to Caffe Model Converter

This is a tutorial of converting Torch pre-trained model to Caffe model for inference. This toolbox is originally provided by facebook AI, but it is kind of out of date and hard to install. We added support for some components (such as batch normalizatin and spatial dropout). This tutorial is trying to save your life from debugging and installation.

Read More


HTML Counter unique visitors since May 2014