# Attention Toward Neighbors: A Context Aware Framework for High Resolution Image Segmentation

arXiv: https://arxiv.org/abs/2106.12902 · HTML: https://mlsanity.com/paper/2106.12902/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 15 references that are in the map.
- First posted on arXiv 24 Jun 2021.

## Builds on (most cited first, 9 of 9)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1802.02611/) (2018)
- [CBAM: Convolutional Block Attention Module](https://mlsanity.com/paper/1807.06521/) (2018)
- [Dual Attention Network for Scene Segmentation](https://mlsanity.com/paper/1809.02983/) (2018)
- [Road Extraction by Deep Residual U-Net](https://mlsanity.com/paper/1711.10684/) (2017)
- [Land-Cover Classification with High-Resolution Remote Sensing Images Using Transferable Deep Models](https://mlsanity.com/paper/1807.05713/) (2018)
- [Fully Convolutional Architectures for Multi-Class Segmentation in Chest Radiographs](https://mlsanity.com/paper/1701.08816/) (2017)

## Built on by (most cited first, 3 of 3)

- [Efficient Leaf Disease Classification and Segmentation using Midpoint Normalization Technique and Attention Mechanism](https://mlsanity.com/paper/2505.21316/) (2025)
- [STLGRU: Spatio-Temporal Lightweight Graph GRU for Traffic Flow Prediction](https://mlsanity.com/paper/2212.04548/) (2022)
- [BD-SAT: High-resolution Land Use Land Cover Dataset & Benchmark Results for Developing Division: Dhaka, BD](https://mlsanity.com/paper/2406.05912/) (2024)

## Abstract (arXiv)

High-resolution image segmentation remains challenging and error-prone due to the enormous size of intermediate feature maps. Conventional methods avoid this problem by using patch based approaches where each patch is segmented independently. However, independent patch segmentation induces errors, particularly at the patch boundary due to the lack of contextual information in very high-resolution images where the patch size is much smaller compared to the full image. To overcome these limitations, in this paper, we propose a novel framework to segment a particular patch by incorporating contextual information from its neighboring patches. This allows the segmentation network to see the target patch with a wider field of view without the need of larger feature maps. Comparative analysis from a number of experiments shows that our proposed framework is able to segment high resolution images with significantly improved mean Intersection over Union and overall accuracy.