Weakly Supervised Object Boundaries
This reduces annotation costs for computer vision tasks, making training more affordable and scalable, though it is incremental as it builds on existing boundary detection methods.
The paper tackles the problem of expensive object boundary annotations by proposing a technique that uses only bounding box annotations to generate weakly supervised data, achieving top performance on object boundary detection and outperforming fully supervised state-of-the-art methods by a large margin.
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.