Efficient Few-Shot Object Detection via Knowledge Inheritance

TL;DR

This paper introduces an efficient few-shot object detection framework that achieves state-of-the-art accuracy while significantly reducing adaptation time, addressing the critical efficiency challenge in embedded AI applications.

Contribution

It proposes a novel pretrain-transfer framework with a knowledge inheritance initializer and adaptive length re-scaling, enabling fast and effective adaptation in few-shot object detection.

Findings

Achieves SOTA results on PASCAL VOC, COCO, and LVIS benchmarks.

Exhibits 1.8-100x faster adaptation speed compared to existing methods.

Maintains competitive accuracy with no additional computational cost.

Abstract

Few-shot object detection (FSOD), which aims at learning a generic detector that can adapt to unseen tasks with scarce training samples, has witnessed consistent improvement recently. However, most existing methods ignore the efficiency issues, e.g., high computational complexity and slow adaptation speed. Notably, efficiency has become an increasingly important evaluation metric for few-shot techniques due to an emerging trend toward embedded AI. To this end, we present an efficient pretrain-transfer framework (PTF) baseline with no computational increment, which achieves comparable results with previous state-of-the-art (SOTA) methods. Upon this baseline, we devise an initializer named knowledge inheritance (KI) to reliably initialize the novel weights for the box classifier, which effectively facilitates the knowledge transfer process and boosts the adaptation speed. Within the KI initializer, we propose an adaptive length re-scaling (ALR) strategy to alleviate the vector length inconsistency between the predicted novel weights and the pretrained base weights. Finally, our approach not only achieves the SOTA results across three public benchmarks, i.e., PASCAL VOC, COCO and LVIS, but also exhibits high efficiency with 1.8-100x faster adaptation speed against the other methods on COCO/LVIS benchmark during few-shot transfer. To our best knowledge, this is the first work to consider the efficiency problem in FSOD. We hope to motivate a trend toward powerful yet efficient few-shot technique development. The codes are publicly available at https://github.com/Ze-Yang/Efficient-FSOD.