Few-shot Object Detection with Refined Contrastive Learning

TL;DR

This paper introduces FSRC, a novel few-shot object detection method that uses refined contrastive learning to better distinguish confusable classes and improve detection consistency, achieving superior results on standard datasets.

Contribution

The paper proposes a new FSOD approach with a pre-determination component and refined contrastive learning to enhance class distinction and detection performance.

Findings

Outperforms state-of-the-art on PASCAL VOC and COCO datasets.

Reduces standard deviation in detection performance.

Improves inter-class separation among confusable classes.

Abstract

Due to the scarcity of sampling data in reality, few-shot object detection (FSOD) has drawn more and more attention because of its ability to quickly train new detection concepts with less data. However, there are still failure identifications due to the difficulty in distinguishing confusable classes. We also notice that the high standard deviation of average precision reveals the inconsistent detection performance. To this end, we propose a novel FSOD method with Refined Contrastive Learning (FSRC). A pre-determination component is introduced to find out the Resemblance Group from novel classes which contains confusable classes. Afterwards, Refined Contrastive Learning (RCL) is pointedly performed on this group of classes in order to increase the inter-class distances among them. In the meantime, the detection results distribute more uniformly which further improve the performance. Experimental results based on PASCAL VOC and COCO datasets demonstrate our proposed method outperforms the current state-of-the-art research.