Group-Wise Semantic Mining for Weakly Supervised Semantic Segmentation

9 Dec 2020  ·  Xueyi Li, Tianfei Zhou, Jianwu Li, Yi Zhou, Zhaoxiang Zhang ·

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 requires 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. We formulate WSSS as a novel group-wise learning task that explicitly models semantic dependencies in a group of images to estimate more reliable pseudo ground-truths, which can be used for training more accurate segmentation models. In particular, we devise a graph neural network (GNN) for group-wise semantic mining, wherein input images are represented as graph nodes, and the underlying relations between a pair of images are characterized by an efficient co-attention mechanism. Moreover, in order to prevent the model from paying excessive attention to common semantics only, we further propose a graph dropout layer, encouraging the model to learn more accurate and complete object responses. The whole network is end-to-end trainable by iterative message passing, which propagates interaction cues over the images to progressively improve the performance. We conduct experiments on the popular PASCAL VOC 2012 and COCO benchmarks, and our model yields state-of-the-art performance. Our code is available at:

PDF Abstract

Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Uses Extra
Training Data
Result Benchmark
Weakly-Supervised Semantic Segmentation COCO 2014 val GroupWSSS mIoU 28.4 # 21
Weakly-Supervised Semantic Segmentation PASCAL VOC 2012 test GroupWSSS Mean IoU 68.5 # 32
Weakly-Supervised Semantic Segmentation PASCAL VOC 2012 val GroupWSSS Mean IoU 68.2 # 34