Integrative Few-Shot Learning for Classification and Segmentation

TL;DR

This paper introduces a new integrative few-shot learning task that combines classification and segmentation, proposing a novel framework and model that perform well on this task and on existing benchmarks.

Contribution

The paper proposes the integrative few-shot learning (iFSL) framework and the ASNet model for simultaneous classification and segmentation in few-shot scenarios.

Findings

Achieves promising results on the FS-CS task.

Sets new state-of-the-art on standard few-shot segmentation benchmarks.

Demonstrates the effectiveness of the proposed model in realistic few-shot episodes.

Abstract

We introduce the integrative task of few-shot classification and segmentation (FS-CS) that aims to both classify and segment target objects in a query image when the target classes are given with a few examples. This task combines two conventional few-shot learning problems, few-shot classification and segmentation. FS-CS generalizes them to more realistic episodes with arbitrary image pairs, where each target class may or may not be present in the query. To address the task, we propose the integrative few-shot learning (iFSL) framework for FS-CS, which trains a learner to construct class-wise foreground maps for multi-label classification and pixel-wise segmentation. We also develop an effective iFSL model, attentive squeeze network (ASNet), that leverages deep semantic correlation and global self-attention to produce reliable foreground maps. In experiments, the proposed method shows promising performance on the FS-CS task and also achieves the state of the art on standard few-shot segmentation benchmarks.