TY - JOUR AU - Han, Guangxing AU - Huang, Shiyuan AU - Ma, Jiawei AU - He, Yicheng AU - Chang, Shih-Fu PY - 2022/06/28 Y2 - 2024/03/29 TI - Meta Faster R-CNN: Towards Accurate Few-Shot Object Detection with Attentive Feature Alignment JF - Proceedings of the AAAI Conference on Artificial Intelligence JA - AAAI VL - 36 IS - 1 SE - AAAI Technical Track on Computer Vision I DO - 10.1609/aaai.v36i1.19959 UR - https://ojs.aaai.org/index.php/AAAI/article/view/19959 SP - 780-789 AB - Few-shot object detection (FSOD) aims to detect objects using only a few examples. How to adapt state-of-the-art object detectors to the few-shot domain remains challenging. Object proposal is a key ingredient in modern object detectors. However, the quality of proposals generated for few-shot classes using existing methods is far worse than that of many-shot classes, e.g., missing boxes for few-shot classes due to misclassification or inaccurate spatial locations with respect to true objects. To address the noisy proposal problem, we propose a novel meta-learning based FSOD model by jointly optimizing the few-shot proposal generation and fine-grained few-shot proposal classification. To improve proposal generation for few-shot classes, we propose to learn a lightweight metric-learning based prototype matching network, instead of the conventional simple linear object/nonobject classifier, e.g., used in RPN. Our non-linear classifier with the feature fusion network could improve the discriminative prototype matching and the proposal recall for few-shot classes. To improve the fine-grained few-shot proposal classification, we propose a novel attentive feature alignment method to address the spatial misalignment between the noisy proposals and few-shot classes, thus improving the performance of few-shot object detection. Meanwhile we learn a separate Faster R-CNN detection head for many-shot base classes and show strong performance of maintaining base-classes knowledge. Our model achieves state-of-the-art performance on multiple FSOD benchmarks over most of the shots and metrics. ER -