Differentiable Meta-learning Model for Few-shot Semantic Segmentation

TL;DR

This paper introduces MetaSegNet, a meta-learning framework for few-shot semantic segmentation that handles multi-object (K-way) scenarios, demonstrating effectiveness on PASCAL VOC and COCO datasets.

Contribution

It proposes a novel meta-learning based framework with an embedding module and a linear base learner for multi-object few-shot segmentation, trained end-to-end.

Findings

Effective on PASCAL VOC dataset

Outperforms existing methods in K-way few-shot segmentation

Handles multi-object segmentation scenarios

Abstract

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.