POODLE: Improving Few-shot Learning via Penalizing Out-of-Distribution Samples

2022/06/08 by Duong Le, Le, Duong H., Khoi Nguyen +8 · 1 citation
Computer Science · Medicine · #COVID-19 diagnosis using AI #Computer Vision and Pattern Recognition (cs.CV) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Machine Learning (cs.LG) #Machine Learning and ELM

paper · pdf · doi:10.48550/arxiv.2206.04679

openalex created_date 2021/11/22 · openalex publication_date 2022/06/08 · openalex updated_date 2026/07/28

Abstract

In this work, we propose to use out-of-distribution samples, i.e., unlabeled samples coming from outside the target classes, to improve few-shot learning. Specifically, we exploit the easily available out-of-distribution samples to drive the classifier to avoid irrelevant features by maximizing the distance from prototypes to out-of-distribution samples while minimizing that of in-distribution samples (i.e., support, query data). Our approach is simple to implement, agnostic to feature extractors, lightweight without any additional cost for pre-training, and applicable to both inductive and transductive settings. Extensive experiments on various standard benchmarks demonstrate that the proposed method consistently improves the performance of pretrained networks with different architectures.

Cited by

• Reliable Few-shot Learning under Dual Noises

Related

• Few-shot Learning with Noisy Labels
• Shot in the Dark: Few-Shot Learning with No Base-Class Labels
• Prototype Rectification for Few-Shot Learning
• EASY: Ensemble Augmented-Shot Y-shaped Learning: State-Of-The-Art Few-Shot Classification with Simple Ingredients
• Few-shot Learning via Dependency Maximization and Instance Discriminant Analysis