A Dense Siamese U-Net trained with Edge Enhanced 3D IOU Loss for Image Co-segmentation

TL;DR

This paper introduces a dense Siamese U-Net with an edge-enhanced 3D IOU loss for improved image co-segmentation, achieving state-of-the-art results by directly estimating signed normalized distance maps from images.

Contribution

The paper proposes a novel dense connection structure in Siamese U-Net and a new edge-enhanced 3D IOU loss based on distance maps for image co-segmentation.

Findings

Achieves state-of-the-art performance on Internet and iCoseg datasets.

Demonstrates the effectiveness of dense connections and edge-enhanced loss.

Improves segmentation accuracy by directly estimating distance maps.

Abstract

Image co-segmentation has attracted a lot of attentions in computer vision community. In this paper, we propose a new approach to image co-segmentation through introducing the dense connections into the decoder path of Siamese U-net and presenting a new edge enhanced 3D IOU loss measured over distance maps. Considering the rigorous mapping between the signed normalized distance map (SNDM) and the binary segmentation mask, we estimate the SNDMs directly from original images and use them to determine the segmentation results. We apply the Siamese U-net for solving this problem and improve its effectiveness by densely connecting each layer with subsequent layers in the decoder path. Furthermore, a new learning loss is designed to measure the 3D intersection over union (IOU) between the generated SNDMs and the labeled SNDMs. The experimental results on commonly used datasets for image co-segmentation demonstrate the effectiveness of our presented dense structure and edge enhanced 3D IOU loss of SNDM. To our best knowledge, they lead to the state-of-the-art performance on the Internet and iCoseg datasets.