期刊
IEEE TRANSACTIONS ON IMAGE PROCESSING
卷 31, 期 -, 页码 799-811出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TIP.2021.3132834
关键词
Semantics; Image segmentation; Training; Location awareness; Cognition; Task analysis; Graph neural networks; Semantic segmentation; weakly supervised learning; group-wise learning; graph neural networks; object localization; neural attention
资金
- Beijing Natural Science Foundation [L191004]
- National Key Research and Development Program of China [2019YFB1310803]
- China Computer Federation (CCF)-Baidu Open Fund
This work proposes a novel group-wise learning framework for weakly supervised semantic segmentation. The framework explicitly encodes semantic dependencies and discovers rich semantic context within a group of images. The proposed model achieves state-of-the-art performance in various benchmarks and demonstrates strong generalizability in weakly supervised object localization tasks.
Acquiring sufficient ground-truth supervision to train deep visual models has been a bottleneck over the years due to the data-hungry nature of deep learning. This is exacerbated in some structured prediction tasks, such as semantic segmentation, which require pixel-level annotations. This work addresses weakly supervised semantic segmentation (WSSS), with the goal of bridging the gap between image-level annotations and pixel-level segmentation. To achieve this, we propose, for the first time, a novel group-wise learning framework for WSSS. The framework explicitly encodes semantic dependencies in a group of images to discover rich semantic context for estimating more reliable pseudo ground-truths, which are subsequently employed to train more effective segmentation models. In particular, we solve the group-wise learning within a graph neural network (GNN), wherein input images are represented as graph nodes, and the underlying relations between a pair of images are characterized by graph edges. We then formulate semantic mining as an iterative reasoning process which propagates the common semantics shared by a group of images to enrich node representations. Moreover, in order to prevent the model from paying excessive attention to common semantics, we further propose a graph dropout layer to encourage the graph model to capture more accurate and complete object responses. With the above efforts, our model lays the foundation for more sophisticated and flexible group-wise semantic mining. We conduct comprehensive experiments on the popular PASCAL VOC 2012 and COCO benchmarks, and our model yields state-of-the-art performance. In addition, our model shows promising performance in weakly supervised object localization (WSOL) on the CUB-200-2011 dataset, demonstrating strong generalizability. Our code is available at: https://github.com/Lixy1997/Group-WSSS.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据