Differentiable Meta-Learning Model for Few-Shot Semantic Segmentation


  • Pinzhuo Tian Nanjing University
  • Zhangkai Wu Nanjing University
  • Lei Qi Nanjing University
  • Lei Wang University of Wollongong
  • Yinghuan Shi Nanjing University
  • Yang Gao Nanjing University




To address the annotation scarcity issue in some cases of semantic segmentation, there have been a few attempts to develop the segmentation model in the few-shot learning paradigm. However, most existing methods only focus on the traditional 1-way segmentation setting (i.e., one image only contains a single object). This is far away from practical semantic segmentation tasks where the K-way setting (K > 1) is usually required by performing the accurate multi-object segmentation. To deal with this issue, we formulate the few-shot semantic segmentation task as a learning-based pixel classification problem, and propose a novel framework called MetaSegNet based on meta-learning. In MetaSegNet, an architecture of embedding module consisting of the global and local feature branches is developed to extract the appropriate meta-knowledge for the few-shot segmentation. Moreover, we incorporate a linear model into MetaSegNet as a base learner to directly predict the label of each pixel for the multi-object segmentation. Furthermore, our MetaSegNet can be trained by the episodic training mechanism in an end-to-end manner from scratch. Experiments on two popular semantic segmentation datasets, i.e., PASCAL VOC and COCO, reveal the effectiveness of the proposed MetaSegNet in the K-way few-shot semantic segmentation task.




How to Cite

Tian, P., Wu, Z., Qi, L., Wang, L., Shi, Y., & Gao, Y. (2020). Differentiable Meta-Learning Model for Few-Shot Semantic Segmentation. Proceedings of the AAAI Conference on Artificial Intelligence, 34(07), 12087-12094. https://doi.org/10.1609/aaai.v34i07.6887



AAAI Technical Track: Vision