We present a framework for efficient perceptual inference that explicitly reasons about the segmentation of its inputs and features. Rather than being trained for any specific segmentation, our framework learns the grouping process in an unsupervised manner or alongside any supervised task. We enable a neural network to group the representations of different objects in an iterative manner through a differentiable mechanism. We achieve very fast convergence by allowing the system to amortize the joint iterative inference of the groupings and their representations. In contrast to many other recently proposed methods for addressing multi-object scenes, our system does not assume the inputs to be images and can therefore directly handle other modalities. We evaluate our method on multi-digit classification of very cluttered images that require texture segmentation. Remarkably our method achieves improved classification performance over convolutional networks despite being fully connected, by making use of the grouping mechanism. Furthermore, we observe that our system greatly improves upon the semi-supervised result of a baseline Ladder network on our dataset. These results are evidence that grouping is a powerful tool that can help to improve sample efficiency.

No abstract

No abstract

Abstract. In this paper, we consider the problem of modeling complex texture information using undirected probabilistic graphical models. Texture is a special type of data that one can better understand by considering its local structure. For that purpose, we propose a convolutional variant of the Gaussian gated Boltzmann machine (GGBM) [12], inspired by the co-occurrence matrix in traditional texture analysis. We also link the proposed model to a much simpler Gaussian restricted Boltzmann machine where convolutional features are computed as a preprocessing step. The usefulness of the model is illustrated in texture classification and reconstruction experiments.

No abstract