Data augmentation is a ubiquitous technique for increasing the size of labeled training sets by leveraging task-specific data transformations that preserve class labels.

Neural Information Processing Systems http://nips.cc/

We show that, compared to earlier works, it is less inclined to be stuck in trivial solutions and avoids the need for a strong generative model.

Typically, inner loops are required to solve the first two sub-minimization problems due to the intractability of the prior and the matrix inversion.

At the same time, the use of deep learning as the basis for neural decoding has received less widespread attention.

With the rapid growth of image and video data on the web, hashing has been extensively studied for image or video search in recent years.

This paper introduces the QMDP-net, a neural network architecture for planning under partial observability. The QMDP-net combines the strengths of model-free learning and model-based planning.

Computer vision tasks often have side information available that is helpful to solve the task. For example, for crowd counting, the camera perspective (e.g., camera angle and height) gives a clue about the appearance and scale of people in the scene. While side information has been shown to be useful for counting systems using traditional hand-crafted features, it has not been fully utilized in counting systems based on deep learning.

Multiple-domain learning contains in turn two sub-challenges.

However, the Achilles' heel of all these approaches is that