Recent advances in the field of artificial intelligence have been made
p...
Small inter-class and large intra-class variations are the main challeng...
Few-shot learning is an important area of research. Conceptually, humans...
This paper presents a novel optimization method for maximizing generaliz...
Transfer-learning and meta-learning are two effective methods to apply
k...
Current state-of-the-art classification and detection algorithms rely on...
Current state-of-the-art classification and detection algorithms rely on...
Deformable Parts Models and Convolutional Networks each have achieved no...
In this paper we address three different computer vision tasks using a s...
Predicting depth is an essential component in understanding the 3D geome...
We present an integrated framework for using Convolutional Networks for
...
Mixtures of Experts combine the outputs of several "expert" networks, ea...
A key challenge in designing convolutional network models is sizing them...