Context-Aware Multipath Networks

TL;DR

CAMNet is a novel multi-path neural network that dynamically routes information based on input context, effectively handling diverse datasets and variations, outperforming traditional models in classification and pixel-labeling tasks.

Contribution

Introduces CAMNet, a data-dependent routing multi-path network that adapts resource allocation according to input context for improved generalization.

Findings

CAMNet outperforms single-path and multi-path networks in classification tasks.

The model effectively captures variations across multiple datasets.

CAMNet controls information flow to distinguish common and domain-specific features.

Abstract

Making a single network effectively address diverse contexts---learning the variations within a dataset or multiple datasets---is an intriguing step towards achieving generalized intelligence. Existing approaches of deepening, widening, and assembling networks are not cost effective in general. In view of this, networks which can allocate resources according to the context of the input and regulate flow of information across the network are effective. In this paper, we present Context-Aware Multipath Network (CAMNet), a multi-path neural network with data-dependant routing between parallel tensors. We show that our model performs as a generalized model capturing variations in individual datasets and multiple different datasets, both simultaneously and sequentially. CAMNet surpasses the performance of classification and pixel-labeling tasks in comparison with the equivalent single-path, multi-path, and deeper single-path networks, considering datasets individually, sequentially, and in combination. The data-dependent routing between tensors in CAMNet enables the model to control the flow of information end-to-end, deciding which resources to be common or domain-specific.