ACNet: Attention Based Network to Exploit Complementary Features for RGBD Semantic Segmentation

Abstract

Compared to RGB semantic segmentation, RGBD semantic segmentation can achieve better performance by taking depth information into consideration. However, it is still problematic for contemporary segmenters to effectively exploit RGBD information since the feature distributions of RGB and depth (D) images vary significantly in different scenes. In this paper, we propose an Attention Complementary Network (ACNet) that selectively gathers features from RGB and depth branches. The main contributions lie in the Attention Complementary Module (ACM) and the architecture with three parallel branches. More precisely, ACM is a channel attention-based module that extracts weighted features from RGB and depth branches. The architecture preserves the inference of the original RGB and depth branches, and enables the fusion branch at the same time. Based on the above structures, ACNet is capable of exploiting more high-quality features from different channels. We evaluate our model on SUN-RGBD and NYUDv2 datasets, and prove that our model outperforms state-of-the-art methods. In particular, a mIoU score of 48.3\% on NYUDv2 test set is achieved with ResNet50. We will release our source code based on PyTorch and the trained segmentation model at https://github.com/anheidelonghu/ACNet.

Accepted to be published in 2019 IEEE International Conference on Image Processing (ICIP 2019), Sep 22-25, 2019, Taipei. IEEE Copyright notice added, 5 pages, 5 figures

References in corpus (2)

• RedNet: Residual Encoder-Decoder Network for indoor RGB-D Semantic Segmentation
• Depth-aware CNN for RGB-D Segmentation

Cited by in corpus (6)

• Bi-directional Cross-Modality Feature Propagation with Separation-and-Aggregation Gate for RGB-D Semantic Segmentation
• Improving Multi-Modal Learning with Uni-Modal Teachers
• Galaxy Image Translation with Semi-supervised Noise-reconstructed Generative Adversarial Networks
• See Clearer at Night: Towards Robust Nighttime Semantic Segmentation through Day-Night Image Conversion
• Hard Pixel Mining for Depth Privileged Semantic Segmentation
• Semantic Segmentation of Panoramic Images Using a Synthetic Dataset