DISIR: Deep Image Segmentation with Interactive Refinement
arXiv:2003.14200 · doi:10.5194/isprs-annals-V-2-2020-877-2020
Abstract
This paper presents an interactive approach for multi-class segmentation of aerial images. Precisely, it is based on a deep neural network which exploits both RGB images and annotations. Starting from an initial output based on the image only, our network then interactively refines this segmentation map using a concatenation of the image and user annotations. Importantly, user annotations modify the inputs of the network - not its weights - enabling a fast and smooth process. Through experiments on two public aerial datasets, we show that user annotations are extremely rewarding: each click corrects roughly 5000 pixels. We analyze the impact of different aspects of our framework such as the representation of the annotations, the volume of training data or the network architecture. Code is available at https://github.com/delair-ai/DISIR.
arXiv comment8 pages, 12 figures. Published in the ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
References in corpus (7)
- Rethinking Atrous Convolution for Semantic Image Segmentation
- Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
- Fully Convolutional Networks for Semantic Segmentation
- Deep Interactive Object Selection
- Fast Interactive Object Annotation with Curve-GCN
- Iteratively Trained Interactive Segmentation
- LEDNet: A Lightweight Encoder-Decoder Network for Real-Time Semantic Segmentation