Hierarchical Multi-Scale Attention for Semantic Segmentation

TL;DR

This paper introduces a hierarchical multi-scale attention mechanism for semantic segmentation that improves accuracy and training efficiency by adaptively combining predictions at different scales, achieving state-of-the-art results.

Contribution

The paper presents a novel hierarchical attention approach for multi-scale prediction fusion, enhancing efficiency and accuracy in semantic segmentation tasks.

Findings

Achieves state-of-the-art results on Cityscapes and Mapillary datasets.

Enables 4x memory efficiency during training.

Improves generalization through auto-labelling on Cityscapes.

Abstract

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).