Energy-based learning is a powerful learning paradigm that encapsulates
...
Neural networks are composed of multiple layers arranged in a hierarchic...
Despite the superior performance of CNN, deploying them on low computati...
In this paper, we consider the problem of non-linear dimensionality redu...
Autoencoders are a type of unsupervised neural networks, which can be us...
Recently, there has been an increasing interest in applying attention
me...
Neural networks are composed of multiple layers arranged in a hierarchic...
spectral-based subspace learning is a common data preprocessing step in ...
Computational color constancy is a preprocessing step used in many camer...
In this paper, we propose a novel unsupervised color constancy method, c...
In this paper, we describe a new large dataset for illumination estimati...
In this paper, we propose a novel color constancy approach, called Bag o...
In this paper, we study the importance of pre-training for the generaliz...