Few-Shot Object Segmentation

Computer vision researchers have been moving beyond simple image classification and tackling more complex tasks such as object localization, detection and semantic segmentation. However, many of the proposed methods require large amounts of annotated data such as segmentation masks, which are expensive and time-consuming to acquire. Moreover, those methods cannot segment new object categories which were not present in the training set.

Few-shot segmentation alleviates both those problems by learning end-to-end to segment new object categories from few examples. In particular, weakly-supervised few-shot object segmentation only requires weak supervision such as sparse pixel annotations, bounding boxes and scribbles, which is substantially easier to gather than dense pixel annotations.

In this project, we propose a few-shot segmentation approach to alleviate the requirement of large strongly supervised datasets. Specifically, we propose a model which can learn how to segment new object categories using only a few annotated examples.

Gabriel Huang
Superviseur universitaire: 
Simon Lacoste-Julien
Partner University: