Weakly Supervised Object Boundaries
arXiv:1511.07803
Abstract
State-of-the-art learning based boundary detection methods require extensive training data. Since labelling object boundaries is one of the most expensive types of annotations, there is a need to relax the requirement to carefully annotate images to make both the training more affordable and to extend the amount of training data. In this paper we propose a technique to generate weakly supervised annotations and show that bounding box annotations alone suffice to reach high-quality object boundaries without using any object-specific boundary annotations. With the proposed weak supervision techniques we achieve the top performance on the object boundary detection task, outperforming by a large margin the current fully supervised state-of-the-art methods.
References in corpus (9)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- What makes for effective detection proposals?
- Multiscale Combinatorial Grouping for Image Segmentation and Object Proposal Generation
- Fast Edge Detection Using Structured Forests
- DeepEdge: A Multi-Scale Bifurcated Deep Network for Top-Down Contour Detection
- Situational Object Boundary Detection
- Oriented Edge Forests for Boundary Detection
- Unsupervised Learning of Edges