Towards Discriminative and Transferable One-Stage Few-Shot Object Detectors
This work improves few-shot object detection for applications with limited annotated data, offering a faster and competitive alternative to existing methods, though it is incremental in advancing one-stage detectors.
The paper tackles the performance gap between two-stage and one-stage few-shot object detectors by addressing weak discriminability due to small receptive fields and limited foreground samples, resulting in FSRN being almost twice as fast as two-stage methods while achieving competitive accuracy on MS-COCO and PASCAL VOC benchmarks.
Recent object detection models require large amounts of annotated data for training a new classes of objects. Few-shot object detection (FSOD) aims to address this problem by learning novel classes given only a few samples. While competitive results have been achieved using two-stage FSOD detectors, typically one-stage FSODs underperform compared to them. We make the observation that the large gap in performance between two-stage and one-stage FSODs are mainly due to their weak discriminability, which is explained by a small post-fusion receptive field and a small number of foreground samples in the loss function. To address these limitations, we propose the Few-shot RetinaNet (FSRN) that consists of: a multi-way support training strategy to augment the number of foreground samples for dense meta-detectors, an early multi-level feature fusion providing a wide receptive field that covers the whole anchor area and two augmentation techniques on query and source images to enhance transferability. Extensive experiments show that the proposed approach addresses the limitations and boosts both discriminability and transferability. FSRN is almost two times faster than two-stage FSODs while remaining competitive in accuracy, and it outperforms the state-of-the-art of one-stage meta-detectors and also some two-stage FSODs on the MS-COCO and PASCAL VOC benchmarks.