High-Order Paired-ASPP Networks for Semantic Segmenation
arXiv:2002.07371
Abstract
Current semantic segmentation models only exploit first-order statistics, while rarely exploring high-order statistics. However, common first-order statistics are insufficient to support a solid unanimous representation. In this paper, we propose High-Order Paired-ASPP Network to exploit high-order statistics from various feature levels. The network first introduces a High-Order Representation module to extract the contextual high-order information from all stages of the backbone. They can provide more semantic clues and discriminative information than the first-order ones. Besides, a Paired-ASPP module is proposed to embed high-order statistics of the early stages into the last stage. It can further preserve the boundary-related and spatial context in the low-level features for final prediction. Our experiments show that the high-order statistics significantly boost the performance on confusing objects. Our method achieves competitive performance without bells and whistles on three benchmarks, i.e, Cityscapes, ADE20K and Pascal-Context with the mIoU of 81.6%, 45.3% and 52.9%.
References in corpus (9)
- A Survey on Deep Learning in Medical Image Analysis
- Rethinking Atrous Convolution for Semantic Image Segmentation
- A Structured Self-attentive Sentence Embedding
- ParseNet: Looking Wider to See Better
- Searching for Efficient Multi-Scale Architectures for Dense Image Prediction
- CCNet: Criss-Cross Attention for Semantic Segmentation
- Dual Attention Network for Scene Segmentation
- Asymmetric Non-local Neural Networks for Semantic Segmentation
- Mixed High-Order Attention Network for Person Re-Identification