Effective Use of Dilated Convolutions for Segmenting Small Object Instances in Remote Sensing Imagery

TL;DR

This paper introduces a novel CNN architecture with a local feature extraction module that improves segmentation of small, crowded objects in high-resolution remote sensing images by addressing the limitations of traditional dilated convolutions.

Contribution

The paper proposes a new LFE module that enhances local feature aggregation in dilated CNNs, specifically improving small object segmentation in remote sensing imagery.

Findings

Significant improvement in small object segmentation accuracy.

Effective handling of crowded and small objects in high-resolution images.

Consistent performance gains across multiple datasets.

Abstract

Thanks to recent advances in CNNs, solid improvements have been made in semantic segmentation of high resolution remote sensing imagery. However, most of the previous works have not fully taken into account the specific difficulties that exist in remote sensing tasks. One of such difficulties is that objects are small and crowded in remote sensing imagery. To tackle with this challenging task we have proposed a novel architecture called local feature extraction (LFE) module attached on top of dilated front-end module. The LFE module is based on our findings that aggressively increasing dilation factors fails to aggregate local features due to sparsity of the kernel, and detrimental to small objects. The proposed LFE module solves this problem by aggregating local features with decreasing dilation factor. We tested our network on three remote sensing datasets and acquired remarkably good results for all datasets especially for small objects.