Hierarchical Multi-Scale Attention for Semantic Segmentation
arXiv:2005.10821
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).
11 pages, 5 figures
References in corpus (5)
Cited by in corpus (24)
- Per-Pixel Classification is Not All You Need for Semantic Segmentation
- Polarized Self-Attention: Towards High-quality Pixel-wise Regression
- PaddleSeg: A High-Efficient Development Toolkit for Image Segmentation
- CitySurfaces: City-Scale Semantic Segmentation of Sidewalk Materials
- A Comprehensive Review of Modern Object Segmentation Approaches
- CCVS: Context-aware Controllable Video Synthesis
- Adaptive Prototype Learning and Allocation for Few-Shot Segmentation
- Tackling Catastrophic Forgetting and Background Shift in Continual Semantic Segmentation
- A Survey on Deep Learning Methods for Semantic Image Segmentation in Real-Time
- ATSal: An Attention Based Architecture for Saliency Prediction in 360 Videos
- Global and Local Features through Gaussian Mixture Models on Image Semantic Segmentation
- Multi-modal anticipation of stochastic trajectories in a dynamic environment with Conditional Variational Autoencoders
- Empirical Study of Multi-Task Hourglass Model for Semantic Segmentation Task
- Improving Road Segmentation in Challenging Domains Using Similar Place Priors
- Boosting Image Outpainting with Semantic Layout Prediction
- ICDAR 2021 Competition on Components Segmentation Task of Document Photos
- Bidirectional Multi-scale Attention Networks for Semantic Segmentation of Oblique UAV Imagery
- Quantifying urban streetscapes with deep learning: focus on aesthetic evaluation
- Perceptual Consistency in Video Segmentation
- 3rd Place Solution for Short-video Face Parsing Challenge
- CASPIANET++: A Multidimensional Channel-Spatial Asymmetric Attention Network with Noisy Student Curriculum Learning Paradigm for Brain Tumor Segmentation
- Semantic Segmentation for Urban-Scene Images
- MetaPix: Domain Transfer for Semantic Segmentation by Meta Pixel Weighting
- TensorX: Extensible API for Neural Network Model Design and Deployment