Effective Use of Dilated Convolutions for Segmenting Small Object Instances in Remote Sensing Imagery
arXiv:1709.00179
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.
References in corpus (13)
- Adam: A Method for Stochastic Optimization
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials
- The Cityscapes Dataset for Semantic Urban Scene Understanding
- What makes for effective detection proposals?
- Convolutional Feature Masking for Joint Object and Stuff Segmentation
- Pyramid Scene Parsing Network
- Fully Convolutional Networks for Dense Semantic Labelling of High-Resolution Aerial Imagery
- Proposal-free Network for Instance-level Object Segmentation
- Automatic Building Extraction in Aerial Scenes Using Convolutional Networks
- PixelNet: Towards a General Pixel-level Architecture
- Fully Convolutional Instance-aware Semantic Segmentation
- Semantic Segmentation of Earth Observation Data Using Multimodal and Multi-scale Deep Networks