An Adaptive Detector for Few Shot Object Detection

Jiming Yan, Hongbo Wang, Xinchen Liu

Abstract: Few-shot object detection has made progress in recent years. However, most research assumes that base and new classes come from the same domain. In real-world applications, they often come from different domains, resulting in poor adaptability of existing methods. To address this problem, we designed an adaptive few-shot object detection framework. Based on the Meta R-CNN framework, we added an image domain classifier after the backbone’s last layer to reduce domain discrepancy. To avoid class feature confusion caused by image feature distribution alignment, we also added a feature filter module (CAFFM) to filter out features irrelevant to specific classes. We tested our method on three base/new splits and found significant performance improvements compared to the base model Meta R-CNN. In base/new split2, mAP50 increased by \(\pm 8 \% \), and in the remaining two splits, mAP50 improved by \(\pm 3 \% \). Our method outperforms state-of-the-art methods in most cases for the three different base/new splits, validating the efficacy and generality of our approach.