Multi-Scale Positive Sample Refinement for Few-Shot Object Detection
This work addresses scale variation challenges in few-shot object detection, which is useful for scenarios with limited annotated data, but it is incremental as it builds on existing Faster R-CNN with FPN architecture.
The paper tackles the problem of scale variations in few-shot object detection by proposing a Multi-scale Positive Sample Refinement approach, which generates object pyramids and refines predictions at various scales, achieving state-of-the-art results on PASCAL VOC and MS COCO datasets.
Few-shot object detection (FSOD) helps detectors adapt to unseen classes with few training instances, and is useful when manual annotation is time-consuming or data acquisition is limited. Unlike previous attempts that exploit few-shot classification techniques to facilitate FSOD, this work highlights the necessity of handling the problem of scale variations, which is challenging due to the unique sample distribution. To this end, we propose a Multi-scale Positive Sample Refinement (MPSR) approach to enrich object scales in FSOD. It generates multi-scale positive samples as object pyramids and refines the prediction at various scales. We demonstrate its advantage by integrating it as an auxiliary branch to the popular architecture of Faster R-CNN with FPN, delivering a strong FSOD solution. Several experiments are conducted on PASCAL VOC and MS COCO, and the proposed approach achieves state of the art results and significantly outperforms other counterparts, which shows its effectiveness. Code is available at https://github.com/jiaxi-wu/MPSR.