D-PCN: Parallel Convolutional Networks for Image Recognition via a Discriminator

TL;DR

D-PCN is a parallel CNN framework with a discriminator that improves feature extraction and achieves state-of-the-art results on CIFAR-100, also benefiting segmentation tasks.

Contribution

Introduces D-PCN, a novel parallel CNN architecture with a discriminator for enhanced feature learning and improved performance across multiple vision tasks.

Findings

State-of-the-art accuracy on CIFAR-100

Improved performance on ImageNet32x32

Enhanced segmentation results 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 complementary representations. The corresponding joint training strategy is introduced which ensures the utilization of discriminator. We validate D-PCN with several CNN models on two benchmark datasets: CIFAR-100 and ImageNet32x32, 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 and verify our motivation. Additionally, we apply D-PCN for segmentation on PASCAL VOC 2012 and also find promotion.