In April, I visited Prof. Bernt Schiele’s Computer Vision and Multimodal Computing Department at the Max Planck Institute for Informatics in Saarbrücken. Aside from a presentation on my recent superpixel benchmark, I also met many interesting people and learned a lot about a career in research.
This article presents a very simple jQuery plugin and the corresponding Wordpress plugin allowing to easily create and reference labels in a LaTeX-style fashion.
Lifting convolutional neural networks to 3D data is challenging due to different data modalities (videos, image volumes, CAD models, LiDAR data etc.) as well as computational limitations (regarding runtime and memory). In this article, I want to summarize several recent papers addressing these problems and tackling different applications such as shape recognition, shape retrieval, medical image segmentation or object detection.
This article discusses how to visualize triangular meshes available in Object File Format (
.off) in Python using occmodel. Installation instructions for installing occmodel on Ubuntu are included.
This article summarizes the reviews corresponding to our paper “Superpixels: An Evaluation of the State-of-the-Art”. The paper was accepted for publication in Computer Vision and Image Understanding. The reviews correspond to v2 on ArXiv. The updated version will be made available on ArXiv.
Many recent deep learning frameworks such as Tensorflow, PyTorch, Theano or Torch are based on dense tensors. However, deep learning on non-tensor data structures is also interesting – especially for sparse, three-dimensional data. This article summarizes some of my experiences regarding deep learning on custom data structures in the mentioned libraries.
This article is a collection of Torch examples meant as introduction to get started with Lua and Torch for deep learning research. The examples can also be considered individually and cover common use cases such as training on CPU and GPU, weight initialization and visualization, custom modules and criteria as well as saving and fine-tuning models.