Papers › Meta-RCNN: Meta Learning for Few-Shot Object Detection

Meta-RCNN: Meta Learning for Few-Shot Object Detection

25 Sep 2019archive 2025-07-28

Xiongwei Wu, Doyen Sahoo, Steven C. H. Hoi

Despite significant advances in object detection in recent years, training effective detectors in a small data regime remains an open challenge. Labelling training data for object detection is extremely expensive, and there is a need to develop techniques that can generalize well from small amounts of labelled data. We investigate this problem of few-shot object detection, where a detector has access to only limited amounts of annotated data. Based on the recently evolving meta-learning principle, we propose a novel meta-learning framework for object detection named ``Meta-RCNN", which learns the ability to perform few-shot detection via meta-learning. Specifically, Meta-RCNN learns an object detector in an episodic learning paradigm on the (meta) training data. This learning scheme helps acquire a prior which enables Meta-RCNN to do few-shot detection on novel tasks. Built on top of the Faster RCNN model, in Meta-RCNN, both the Region Proposal Network (RPN) and the object classification branch are meta-learned. The meta-trained RPN learns to provide class-specific proposals, while the object classifier learns to do few-shot classification. The novel loss objectives and learning strategy of Meta-RCNN can be trained in an end-to-end manner. We demonstrate the effectiveness of Meta-RCNN in addressing few-shot detection on Pascal VOC dataset and achieve promising results.

PaperPDF

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Cross-Domain Few-Shot Object DetectionFew-Shot Object DetectionMeta-LearningObjectObject DetectionRegion Proposalobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Cross-Domain Few-Shot Object Detection Artaxor Meta-RCNN mAP 14.0 #13 of 16 Archive leaderboard report
Cross-Domain Few-Shot Object Detection DIOR Meta-RCNN mAP 20.6 #9 of 15 Archive leaderboard report
Cross-Domain Few-Shot Object Detection UODD Meta-RCNN mAP 11.2 #12 of 16 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections