Stacked Deconvolutional Network for Semantic Segmentation

TL;DR

This paper introduces a Stacked Deconvolutional Network (SDN) that stacks multiple shallow deconvolutional units with hierarchical supervision and enhanced connections, achieving state-of-the-art results in semantic segmentation.

Contribution

The paper proposes a novel SDN architecture with inter-unit and intra-unit connections and hierarchical supervision to improve semantic segmentation accuracy.

Findings

Achieved 86.6% IoU on PASCAL VOC 2012 without CRF post-processing.

Set new state-of-the-art results on CamVid and GATECH datasets.

Demonstrated effective feature fusion and localization recovery in segmentation.

Abstract

Recent progress in semantic segmentation has been driven by improving the spatial resolution under Fully Convolutional Networks (FCNs). To address this problem, we propose a Stacked Deconvolutional Network (SDN) for semantic segmentation. In SDN, multiple shallow deconvolutional networks, which are called as SDN units, are stacked one by one to integrate contextual information and guarantee the fine recovery of localization information. Meanwhile, inter-unit and intra-unit connections are designed to assist network training and enhance feature fusion since the connections improve the flow of information and gradient propagation throughout the network. Besides, hierarchical supervision is applied during the upsampling process of each SDN unit, which guarantees the discrimination of feature representations and benefits the network optimization. We carry out comprehensive experiments and achieve the new state-of-the-art results on three datasets, including PASCAL VOC 2012, CamVid, GATECH. In particular, our best model without CRF post-processing achieves an intersection-over-union score of 86.6% in the test set.