Hierarchical Multi-Scale Attention for Semantic Segmentation

21 May 2020  ·  Andrew Tao, Karan Sapra, Bryan Catanzaro ·

Multi-scale inference is commonly used to improve the results of semantic segmentation. Multiple images scales are passed through a network and then the results are combined with averaging or max pooling. In this work, we present an attention-based approach to combining multi-scale predictions. We show that predictions at certain scales are better at resolving particular failures modes, and that the network learns to favor those scales for such cases in order to generate better predictions. Our attention mechanism is hierarchical, which enables it to be roughly 4x more memory efficient to train than other recent approaches. In addition to enabling faster training, this allows us to train with larger crop sizes which leads to greater model accuracy. We demonstrate the result of our method on two datasets: Cityscapes and Mapillary Vistas. For Cityscapes, which has a large number of weakly labelled images, we also leverage auto-labelling to improve generalization. Using our approach we achieve a new state-of-the-art results in both Mapillary (61.1 IOU val) and Cityscapes (85.1 IOU test).

PDF Abstract

Results from the Paper

Ranked #2 on Semantic Segmentation on Cityscapes val (using extra training data)

     Get a GitHub badge
Task Dataset Model Metric Name Metric Value Global Rank Uses Extra
Training Data
Result Benchmark
Semantic Segmentation Cityscapes val HRNet-OCR mIoU 86.3 # 2
Panoptic Segmentation Mapillary val HRNet-OCR (Hierarchical Multi-Scale Attention) PQ 17.6 # 8


No methods listed for this paper. Add relevant methods here