RCANET: ROW-COLUMN ATTENTION NETWORK FOR SEMANTIC SEGMENTATION

Establishing high-order interactions among pixels and object parts is one of the most fundamental problems in semantic segmentation. The recent proposals are based on non-local methods which utilize the self-attention mechanism to capture the long-range correlations. However, non-local methods could be very expensive, both theoretically and experimentally. Moreover, non-local methods are typically designed to address spatial correlations rather than feature correlations across channels. In this work, we propose a Row-Column Attention Network (RCANet) to encode globally contextual information. It consists of a row-wise intra-channel attention module and a column-wise intra-channel attention module, followed by a cross-channel interaction module. We conduct experiments on two datasets: Cityscapes and ADE20K. The results show that our method is comparable to the state-of-the-art methods for semantic segmentation.