RedNet: Residual Encoder-Decoder Network for indoor RGB-D Semantic Segmentation

4 Jun 2018  ·  Jindong Jiang, Lunan Zheng, Fei Luo, Zhijun Zhang ·

Indoor semantic segmentation has always been a difficult task in computer vision. In this paper, we propose an RGB-D residual encoder-decoder architecture, named RedNet, for indoor RGB-D semantic segmentation. In RedNet, the residual module is applied to both the encoder and decoder as the basic building block, and the skip-connection is used to bypass the spatial feature between the encoder and decoder. In order to incorporate the depth information of the scene, a fusion structure is constructed, which makes inference on RGB image and depth image separately, and fuses their features over several layers. In order to efficiently optimize the network's parameters, we propose a `pyramid supervision' training scheme, which applies supervised learning over different layers in the decoder, to cope with the problem of gradients vanishing. Experiment results show that the proposed RedNet(ResNet-50) achieves a state-of-the-art mIoU accuracy of 47.8% on the SUN RGB-D benchmark dataset.

PDF Abstract

Datasets


Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Semantic Segmentation RSMSS RedNet mIoU 62.3% # 4
Semantic Segmentation SUN-RGBD RedNet (ResNet-50) Mean IoU 47.8% # 16

Methods


No methods listed for this paper. Add relevant methods here