Few-Shot Object Detection via Knowledge Transfer

TL;DR

This paper proposes a few-shot object detection method that leverages knowledge transfer and prototype prediction with a graph-structured approach, enabling effective detection with minimal training data.

Contribution

It introduces a novel prototype-based knowledge transfer framework with a graph-structured predictor for few-shot object detection.

Findings

Effective detection of novel categories with few examples.

Outperforms baseline methods on PASCAL VOC dataset.

Utilizes graph-structured prototypes for improved knowledge transfer.

Abstract

Conventional methods for object detection usually require substantial amounts of training data and annotated bounding boxes. If there are only a few training data and annotations, the object detectors easily overfit and fail to generalize. It exposes the practical weakness of the object detectors. On the other hand, human can easily master new reasoning rules with only a few demonstrations using previously learned knowledge. In this paper, we introduce a few-shot object detection via knowledge transfer, which aims to detect objects from a few training examples. Central to our method is prototypical knowledge transfer with an attached meta-learner. The meta-learner takes support set images that include the few examples of the novel categories and base categories, and predicts prototypes that represent each category as a vector. Then, the prototypes reweight each RoI (Region-of-Interest) feature vector from a query image to remodels R-CNN predictor heads. To facilitate the remodeling process, we predict the prototypes under a graph structure, which propagates information of the correlated base categories to the novel categories with explicit guidance of prior knowledge that represents correlations among categories. Extensive experiments on the PASCAL VOC dataset verifies the effectiveness of the proposed method.