CDFormer: Cross-Domain Few-Shot Object Detection Transformer Against Feature Confusion

TL;DR

CDFormer is a novel transformer-based approach for cross-domain few-shot object detection that effectively addresses feature confusion through specialized modules, significantly improving detection performance across various shot settings.

Contribution

The paper introduces CDFormer, which employs object-background and object-object distinguishing modules to mitigate feature confusion in cross-domain few-shot detection tasks.

Findings

Achieves up to 12.9% mAP improvement over previous methods.

Effectively differentiates objects from background and between classes.

Demonstrates strong performance across 1/5/10 shot settings.

Abstract

Cross-domain few-shot object detection (CD-FSOD) aims to detect novel objects across different domains with limited class instances. Feature confusion, including object-background confusion and object-object confusion, presents significant challenges in both cross-domain and few-shot settings. In this work, we introduce CDFormer, a cross-domain few-shot object detection transformer against feature confusion, to address these challenges. The method specifically tackles feature confusion through two key modules: object-background distinguishing (OBD) and object-object distinguishing (OOD). The OBD module leverages a learnable background token to differentiate between objects and background, while the OOD module enhances the distinction between objects of different classes. Experimental results demonstrate that CDFormer outperforms previous state-of-the-art approaches, achieving 12.9% mAP, 11.0% mAP, and 10.4% mAP improvements under the 1/5/10 shot settings, respectively, when fine-tuned.