What's the Point: Semantic Segmentation with Point Supervision
arXiv:1506.02106
Abstract
The semantic image segmentation task presents a trade-off between test time accuracy and training-time annotation cost. Detailed per-pixel annotations enable training accurate models but are very time-consuming to obtain, image-level class labels are an order of magnitude cheaper but result in less accurate models. We take a natural step from image-level annotation towards stronger supervision: we ask annotators to point to an object if one exists. We incorporate this point supervision along with a novel objectness potential in the training loss function of a CNN model. Experimental results on the PASCAL VOC 2012 benchmark reveal that the combined effect of point-level supervision and objectness potential yields an improvement of 12.9% mIOU over image-level supervision. Further, we demonstrate that models trained with point-level supervision are more accurate than models trained with image-level, squiggle-level or full supervision given a fixed annotation budget.
ECCV (2016) submission
References in corpus (4)
Cited by in corpus (12)
- The Cityscapes Dataset for Semantic Urban Scene Understanding
- Deep Weakly-Supervised Learning Methods for Classification and Localization in Histology Images: A Survey
- Simple Does It: Weakly Supervised Instance and Semantic Segmentation
- Exploiting saliency for object segmentation from image level labels
- Pointly-Supervised Action Localization
- Scribble Hides Class: Promoting Scribble-Based Weakly-Supervised Semantic Segmentation with Its Class Label
- Automatic Lymphocyte Detection in H&E Images with Deep Neural Networks
- Surveillance Video Parsing with Single Frame Supervision
- Adaptive Binarization for Weakly Supervised Affordance Segmentation
- LOST: A flexible framework for semi-automatic image annotation
- ScribbleSup: Scribble-Supervised Convolutional Networks for Semantic Segmentation
- Learning Rich Representations For Structured Visual Prediction Tasks