Cross-Image Region Mining with Region Prototypical Network for Weakly Supervised Segmentation
arXiv:2108.07413
Abstract
Weakly supervised image segmentation trained with image-level labels usually suffers from inaccurate coverage of object areas during the generation of the pseudo groundtruth. This is because the object activation maps are trained with the classification objective and lack the ability to generalize. To improve the generality of the objective activation maps, we propose a region prototypical network RPNet to explore the cross-image object diversity of the training set. Similar object parts across images are identified via region feature comparison. Object confidence is propagated between regions to discover new object areas while background regions are suppressed. Experiments show that the proposed method generates more complete and accurate pseudo object masks, while achieving state-of-the-art performance on PASCAL VOC 2012 and MS COCO. In addition, we investigate the robustness of the proposed method on reduced training sets.
References in corpus (9)
- Prototypical Networks for Few-shot Learning
- Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials
- ParseNet: Looking Wider to See Better
- STC: A Simple to Complex Framework for Weakly-supervised Semantic Segmentation
- Weakly- and Semi-Supervised Learning of a DCNN for Semantic Image Segmentation
- Depth Adaptive Deep Neural Network for Semantic Segmentation
- Few-Shot Segmentation with Global and Local Contrastive Learning
- Inter-Image Communication for Weakly Supervised Localization
- Remember What You have drawn: Semantic Image Manipulation with Memory