Domain Adaptive Few-Shot Open-Set Learning

TL;DR

This paper introduces DAFOSNET, a novel meta-learning framework for domain adaptive few-shot open-set recognition that effectively identifies outliers and manages domain shifts using adversarial augmentation and prototype alignment.

Contribution

It proposes a comprehensive approach combining pseudo open-space decision boundaries, adversarial data augmentation, and domain-specific prototype alignment for improved open-set recognition under domain shifts.

Findings

DAFOSNET outperforms existing methods on multiple benchmarks.

The model effectively detects outliers in target domains.

Adversarial augmentation improves data density and model robustness.

Abstract

Few-shot learning has made impressive strides in addressing the crucial challenges of recognizing unknown samples from novel classes in target query sets and managing visual shifts between domains. However, existing techniques fall short when it comes to identifying target outliers under domain shifts by learning to reject pseudo-outliers from the source domain, resulting in an incomplete solution to both problems. To address these challenges comprehensively, we propose a novel approach called Domain Adaptive Few-Shot Open Set Recognition (DA-FSOS) and introduce a meta-learning-based architecture named DAFOSNET. During training, our model learns a shared and discriminative embedding space while creating a pseudo open-space decision boundary, given a fully-supervised source domain and a label-disjoint few-shot target domain. To enhance data density, we use a pair of conditional adversarial networks with tunable noise variances to augment both domains closed and pseudo-open spaces. Furthermore, we propose a domain-specific batch-normalized class prototypes alignment strategy to align both domains globally while ensuring class-discriminativeness through novel metric objectives. Our training approach ensures that DAFOS-NET can generalize well to new scenarios in the target domain. We present three benchmarks for DA-FSOS based on the Office-Home, mini-ImageNet/CUB, and DomainNet datasets and demonstrate the efficacy of DAFOS-NET through extensive experimentation