Label, Verify, Correct: A Simple Few Shot Object Detection Method
Prannay Kaul, Weidi Xie, Andrew Zisserman

TL;DR
This paper presents a straightforward pseudo-labeling approach for few-shot object detection that enhances training data quality through verification and correction, leading to state-of-the-art results on standard benchmarks.
Contribution
The paper introduces a simple yet effective pseudo-labeling method with verification and correction steps to improve few-shot object detection performance.
Findings
Achieves state-of-the-art results on PASCAL VOC and MS-COCO datasets.
Maintains performance on base classes while improving few-shot detection.
Simple augmentations further enhance detection accuracy.
Abstract
The objective of this paper is few-shot object detection (FSOD) -- the task of expanding an object detector for a new category given only a few instances for training. We introduce a simple pseudo-labelling method to source high-quality pseudo-annotations from the training set, for each new category, vastly increasing the number of training instances and reducing class imbalance; our method finds previously unlabelled instances. Na\"ively training with model predictions yields sub-optimal performance; we present two novel methods to improve the precision of the pseudo-labelling process: first, we introduce a verification technique to remove candidate detections with incorrect class labels; second, we train a specialised model to correct poor quality bounding boxes. After these two novel steps, we obtain a large set of high-quality pseudo-annotations that allow our final detector to be…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdvanced Neural Network Applications · Domain Adaptation and Few-Shot Learning · Advanced Image and Video Retrieval Techniques
MethodsBalanced Selection
