InfRS: Incremental Few-Shot Object Detection in Remote Sensing Images

TL;DR

This paper presents InfRS, a novel incremental few-shot object detection method for remote sensing images that leverages prototype-based learning and Wasserstein distance calibration to effectively recognize new classes while retaining knowledge of existing ones.

Contribution

The paper introduces a fine-tuning-based incremental learning approach with a Hybrid Prototypical Contrastive encoding and Wasserstein distance calibration for remote sensing images.

Findings

Effective detection of new classes with limited data

Preserves performance on base classes without revisiting previous data

Outperforms existing methods on NWPU VHR-10 and DIOR datasets

Abstract

Recently, the field of few-shot detection within remote sensing imagery has witnessed significant advancements. Despite these progresses, the capacity for continuous conceptual learning still poses a significant challenge to existing methodologies. In this paper, we explore the intricate task of incremental few-shot object detection in remote sensing images. We introduce a pioneering fine-tuningbased technique, termed InfRS, designed to facilitate the incremental learning of novel classes using a restricted set of examples, while concurrently preserving the performance on established base classes without the need to revisit previous datasets. Specifically, we pretrain the model using abundant data from base classes and then generate a set of class-wise prototypes that represent the intrinsic characteristics of the data. In the incremental learning stage, we introduce a Hybrid Prototypical Contrastive (HPC) encoding module for learning discriminative representations. Furthermore, we develop a prototypical calibration strategy based on the Wasserstein distance to mitigate the catastrophic forgetting problem. Comprehensive evaluations on the NWPU VHR-10 and DIOR datasets demonstrate that our model can effectively solve the iFSOD problem in remote sensing images. Code will be released.