High-Order Paired-ASPP Networks for Semantic Segmenation
This work addresses the challenge of improving semantic segmentation accuracy for confusing objects, representing an incremental advancement in the field.
The paper tackles the problem of insufficient first-order statistics in semantic segmentation by proposing a High-Order Paired-ASPP Network to exploit high-order statistics from various feature levels, achieving mIoU scores of 81.6% on Cityscapes, 45.3% on ADE20K, and 52.9% on Pascal-Context.
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%.