Multi Receptive Field Network for Semantic Segmentation

TL;DR

This paper introduces a Multi-Receptive Field Network with an edge-aware loss for semantic segmentation, effectively handling multi-scale objects and boundary precision, achieving state-of-the-art results on Cityscapes and Pascal VOC2012 datasets.

Contribution

The paper proposes a novel Multi-Receptive Field Module and an edge-aware loss to improve multi-scale feature integration and boundary accuracy in semantic segmentation.

Findings

Achieved 83.0 mean IoU on Cityscapes dataset.

Achieved 88.4 mean IoU on Pascal VOC2012 dataset.

Outperformed existing methods on benchmark datasets.

Abstract

Semantic segmentation is one of the key tasks in computer vision, which is to assign a category label to each pixel in an image. Despite significant progress achieved recently, most existing methods still suffer from two challenging issues: 1) the size of objects and stuff in an image can be very diverse, demanding for incorporating multi-scale features into the fully convolutional networks (FCNs); 2) the pixels close to or at the boundaries of object/stuff are hard to classify due to the intrinsic weakness of convolutional networks. To address the first issue, we propose a new Multi-Receptive Field Module (MRFM), explicitly taking multi-scale features into account. For the second issue, we design an edge-aware loss which is effective in distinguishing the boundaries of object/stuff. With these two designs, our Multi Receptive Field Network achieves new state-of-the-art results on two widely-used semantic segmentation benchmark datasets. Specifically, we achieve a mean IoU of 83.0 on the Cityscapes dataset and 88.4 mean IoU on the Pascal VOC2012 dataset.