Preprint Article Version 1 Preserved in Portico This version is not peer-reviewed

Task-Adaptive Embedding Learning with Dynamic Kernel Fusion for Few-Shot Remote Sensing Scene Classification

Version 1 : Received: 17 August 2021 / Approved: 18 August 2021 / Online: 18 August 2021 (14:29:29 CEST)

A peer-reviewed article of this Preprint also exists.

Zhang, P.; Fan, G.; Wu, C.; Wang, D.; Li, Y. Task-Adaptive Embedding Learning with Dynamic Kernel Fusion for Few-Shot Remote Sensing Scene Classification. Remote Sens. 2021, 13, 4200. Zhang, P.; Fan, G.; Wu, C.; Wang, D.; Li, Y. Task-Adaptive Embedding Learning with Dynamic Kernel Fusion for Few-Shot Remote Sensing Scene Classification. Remote Sens. 2021, 13, 4200.

Journal reference: Remote Sens. 2021, 13, 4200
DOI: 10.3390/rs13214200

Abstract

The central goal of few-shot scene classification is to learn a model that can generalize well to a novel scene category (UNSEEN) from only one or a few labeled examples. Recent works in the remote sensing (RS) community tackle this challenge by developing algorithms in a meta-learning manner. However, most prior approaches have either focused on rapidly optimizing a meta-learner or aimed at finding good similarity metrics while overlooking the embedding power. Here we propose a novel Task-Adaptive Embedding Learning (TAEL) framework that complements the existing methods by giving full play to feature embedding’s dual roles in few-shot scene classification - representing images and constructing classifiers in the embedding space. First, we design a lightweight network that enriches the diversity and expressive capacity of embeddings by dynamically fusing information from multiple kernels. Second, we present a task-adaptive strategy that helps to generate more discriminative representations by transforming the universal embeddings into task-specific embeddings via a self-attention mechanism. We evaluate our model in the standard few-shot learning setting on two challenging datasets: NWPU-RESISC4 and RSD46-WHU. Experimental results demonstrate that, on all tasks, our method achieves state-of-the-art performance by a significant margin.

Keywords

remote-sensing classification; scene classification; few-shot learning; meta-learning; vision transformers; multi-scale feature fusion

Subject

MATHEMATICS & COMPUTER SCIENCE, Other

Comments (0)

We encourage comments and feedback from a broad range of readers. See criteria for comments and our diversity statement.

Leave a public comment
Send a private comment to the author(s)
Views 0
Downloads 0
Comments 0
Metrics 0


×
Alerts
Notify me about updates to this article or when a peer-reviewed version is published.
We use cookies on our website to ensure you get the best experience.
Read more about our cookies here.