Asymmetric Non-local Neural Networks for Semantic Segmentation

The non-local module works as a particularly useful technique for semantic segmentation while criticized for its prohibitive computation and GPU memory occupation. In this paper, we present Asymmetric Non-local Neural Network to semantic segmentation, which has two prominent components: Asymmetric Pyramid Non-local Block (APNB) and Asymmetric Fusion Non-local Block (AFNB). APNB leverages a pyramid sampling module into the non-local block to largely reduce the computation and memory consumption without sacrificing the performance. AFNB is adapted from APNB to fuse the features of different levels under a sufficient consideration of long range dependencies and thus considerably improves the performance. Extensive experiments on semantic segmentation benchmarks demonstrate the effectiveness and efficiency of our work. In particular, we report the state-of-the-art performance of 81.3 mIoU on the Cityscapes test set. For a 256x128 input, APNB is around 6 times faster than a non-local block on GPU while 28 times smaller in GPU running memory occupation. Code is available at:

PDF Abstract ICCV 2019 PDF ICCV 2019 Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Semantic Segmentation ADE20K Asymmetric ALNN Validation mIoU 45.24 # 168
Semantic Segmentation ADE20K val Asymmetric ALNN mIoU 45.24 # 77
Semantic Segmentation Cityscapes test Asymmetric ALNN Mean IoU (class) 81.3% # 38
Semantic Segmentation COCO-Stuff test Asymmetric ALNN mIoU 37.2% # 15
Semantic Segmentation PASCAL Context Asymmetric ALNN mIoU 52.8 # 41