# Weakly Supervised Object Boundaries

arXiv: https://arxiv.org/abs/1511.07803 · HTML: https://mlsanity.com/paper/1511.07803/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Nov 2015.

## Built on by (most cited first, 4 of 4)

- [Learning Crisp Boundaries Using Deep Refinement Network and Adaptive Weighting Loss](https://mlsanity.com/paper/2102.01301/) (2021)
- [Prompting DirectSAM for Semantic Contour Extraction in Remote Sensing Images](https://mlsanity.com/paper/2410.06194/) (2024)
- [Learning to Detect Semantic Boundaries with Image-level Class Labels](https://mlsanity.com/paper/2212.07579/) (2022)
- [Robust Unsupervised Domain Adaptation by Retaining Confident Entropy via Edge Concatenation](https://mlsanity.com/paper/2310.07149/) (2023)

## Abstract (arXiv)

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.