Directed Variational Cross-encoder Network for Few-shot Multi-image Co-segmentation

TL;DR

This paper introduces DVICE, a class-agnostic, few-shot multi-image co-segmentation framework that leverages a novel encoder-decoder network and meta-learning to outperform existing methods on small datasets.

Contribution

The paper presents a new class-agnostic, few-shot co-segmentation approach using the DVICE network and meta-learning, addressing small dataset challenges.

Findings

Outperforms state-of-the-art co-segmentation methods on multiple datasets.

Effective with limited training data, demonstrating robustness.

Does not rely on semantic class labels, enabling broader applicability.

Abstract

In this paper, we propose a novel framework for multi-image co-segmentation using class agnostic meta-learning strategy by generalizing to new classes given only a small number of training samples for each new class. We have developed a novel encoder-decoder network termed as DVICE (Directed Variational Inference Cross Encoder), which learns a continuous embedding space to ensure better similarity learning. We employ a combination of the proposed DVICE network and a novel few-shot learning approach to tackle the small sample size problem encountered in co-segmentation with small datasets like iCoseg and MSRC. Furthermore, the proposed framework does not use any semantic class labels and is entirely class agnostic. Through exhaustive experimentation over multiple datasets using only a small volume of training data, we have demonstrated that our approach outperforms all existing state-of-the-art techniques.