# Attention to Refine through Multi-Scales for Semantic Segmentation

arXiv: https://arxiv.org/abs/1807.02917 · HTML: https://mlsanity.com/paper/1807.02917/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Jul 2018.

## Built on by (most cited first, 5 of 5)

- [HRDA: Context-Aware High-Resolution Domain-Adaptive Semantic Segmentation](https://mlsanity.com/paper/2204.13132/) (2022)
- [Domain Adaptive and Generalizable Network Architectures and Training Strategies for Semantic Image Segmentation](https://mlsanity.com/paper/2304.13615/) (2023)
- [FastSurferVINN: Building Resolution-Independence into Deep Learning Segmentation Methods -- A Solution for HighRes Brain MRI](https://mlsanity.com/paper/2112.09654/) (2021)
- [Dense Prediction with Attentive Feature Aggregation](https://mlsanity.com/paper/2111.00770/) (2021)
- [Semantic Segmentation for Real-World and Synthetic Vehicle's Forward-Facing Camera Images](https://mlsanity.com/paper/2407.05452/) (2024)

## Abstract (arXiv)

This paper proposes a novel attention model for semantic segmentation, which aggregates multi-scale and context features to refine prediction. Specifically, the skeleton convolutional neural network framework takes in multiple different scales inputs, by which means the CNN can get representations in different scales. The proposed attention model will handle the features from different scale streams respectively and integrate them. Then location attention branch of the model learns to softly weight the multi-scale features at each pixel location. Moreover, we add an recalibrating branch, parallel to where location attention comes out, to recalibrate the score map per class. We achieve quite competitive results on PASCAL VOC 2012 and ADE20K datasets, which surpass baseline and related works.