AcroFOD: An Adaptive Method for Cross-domain Few-shot Object Detection

TL;DR

This paper introduces AcroFOD, an adaptive approach for cross-domain few-shot object detection that intelligently selects and augments data to improve detection performance under domain shift with limited target data.

Contribution

It presents an adaptive optimization strategy for data selection and a multi-level domain-aware augmentation to enhance detection in target domains with scarce data.

Findings

Achieves state-of-the-art results on multiple benchmarks.

Effectively filters augmented data to match target feature distribution.

Improves detection accuracy with limited target samples.

Abstract

Under the domain shift, cross-domain few-shot object detection aims to adapt object detectors in the target domain with a few annotated target data. There exists two significant challenges: (1) Highly insufficient target domain data; (2) Potential over-adaptation and misleading caused by inappropriately amplified target samples without any restriction. To address these challenges, we propose an adaptive method consisting of two parts. First, we propose an adaptive optimization strategy to select augmented data similar to target samples rather than blindly increasing the amount. Specifically, we filter the augmented candidates which significantly deviate from the target feature distribution in the very beginning. Second, to further relieve the data limitation, we propose the multi-level domain-aware data augmentation to increase the diversity and rationality of augmented data, which exploits the cross-image foreground-background mixture. Experiments show that the proposed method achieves state-of-the-art performance on multiple benchmarks.