Semi-Supervised Object Detection with Sparsely Annotated Dataset

TL;DR

This paper introduces a semi-supervised object detection method that leverages single object tracking on sparsely annotated datasets to generate dense training labels, improving detection performance.

Contribution

The paper proposes a novel semi-supervised approach combining anchorless detection and object tracking to enhance training with sparse annotations.

Findings

Achieved runner-up in the Epic-Kitchens challenge's Unseen section.

Secured first place in the Seen section of the challenge.

Demonstrated effectiveness of tracking-based label generation for sparse datasets.

Abstract

In training object detector based on convolutional neural networks, selection of effective positive examples for training is an important factor. However, when training an anchor-based detectors with sparse annotations on an image, effort to find effective positive examples can hinder training performance. When using the anchor-based training for the ground truth bounding box to collect positive examples under given IoU, it is often possible to include objects from other classes in the current training class, or objects that are needed to be trained can only be sampled as negative examples. We used two approaches to solve this problem: 1) the use of an anchorless object detector and 2) a semi-supervised learning-based object detection using a single object tracker. The proposed technique performs single object tracking by using the sparsely annotated bounding box as an anchor in the temporal domain for successive frames. From the tracking results, dense annotations for training images were generated in an automated manner and used for training the object detector. We applied the proposed single object tracking-based semi-supervised learning to the Epic-Kitchens dataset. As a result, we were able to achieve \textbf{runner-up} performance in the Unseen section while achieving the first place in the Seen section of the Epic-Kitchens 2020 object detection challenge under IoU > 0.5 evaluation