Parallel Convolutional Networks for Image Recognition via a Discriminator

TL;DR

This paper presents D-PCN, a parallel CNN framework with a discriminator that improves feature extraction and achieves state-of-the-art results on CIFAR-100 and benefits segmentation tasks.

Contribution

The paper introduces D-PCN, a novel parallel CNN architecture with a discriminator that enhances feature diversity and improves recognition performance.

Findings

D-PCN outperforms baseline models on CIFAR-100.

D-PCN achieves state-of-the-art results on CIFAR-100.

D-PCN improves segmentation performance on PASCAL VOC 2012.

Abstract

In this paper, we introduce a simple but quite effective recognition framework dubbed D-PCN, aiming at enhancing feature extracting ability of CNN. The framework consists of two parallel CNNs, a discriminator and an extra classifier which takes integrated features from parallel networks and gives final prediction. The discriminator is core which drives parallel networks to focus on different regions and learn different representations. The corresponding training strategy is introduced to ensures utilization of discriminator. We validate D-PCN with several CNN models on benchmark datasets: CIFAR-100, and ImageNet, D-PCN enhances all models. In particular it yields state of the art performance on CIFAR-100 compared with related works. We also conduct visualization experiment on fine-grained Stanford Dogs dataset to verify our motivation. Additionally, we apply D-PCN for segmentation on PASCAL VOC 2012 and also find promotion.