Convolutional Neural Networks with Alternately Updated Clique

TL;DR

This paper introduces CliqueNet, a novel CNN architecture with alternately updated loops and bidirectional connections that enhance information flow, improve feature refinement, and achieve state-of-the-art results on multiple image recognition datasets.

Contribution

The paper presents a new CNN architecture with a recurrent feedback loop and bidirectional layer connections, improving information flow and feature refinement over prior models.

Findings

Achieves state-of-the-art performance on CIFAR-10, CIFAR-100, SVHN, and ImageNet.

Uses fewer parameters while maintaining high accuracy.

Demonstrates effective feature refinement through multi-scale strategies.

Abstract

Improving information flow in deep networks helps to ease the training difficulties and utilize parameters more efficiently. Here we propose a new convolutional neural network architecture with alternately updated clique (CliqueNet). In contrast to prior networks, there are both forward and backward connections between any two layers in the same block. The layers are constructed as a loop and are updated alternately. The CliqueNet has some unique properties. For each layer, it is both the input and output of any other layer in the same block, so that the information flow among layers is maximized. During propagation, the newly updated layers are concatenated to re-update previously updated layer, and parameters are reused for multiple times. This recurrent feedback structure is able to bring higher level visual information back to refine low-level filters and achieve spatial attention. We analyze the features generated at different stages and observe that using refined features leads to a better result. We adopt a multi-scale feature strategy that effectively avoids the progressive growth of parameters. Experiments on image recognition datasets including CIFAR-10, CIFAR-100, SVHN and ImageNet show that our proposed models achieve the state-of-the-art performance with fewer parameters.