MVA2023 Small Object Detection Challenge for Spotting Birds: Dataset, Methods, and Results

TL;DR

This paper introduces a new small object detection dataset focused on spotting birds, details a challenge involving over 200 participants, and shares top methods and results for advancing bird detection in challenging images.

Contribution

It presents the SOD4SB dataset, the first large-scale bird detection dataset for small objects, and reports on a challenge with innovative methods and results.

Findings

223 participants in the challenge

Introduction of the SOD4SB dataset with 137,121 bird instances

Baseline code and evaluation website provided

Abstract

Small Object Detection (SOD) is an important machine vision topic because (i) a variety of real-world applications require object detection for distant objects and (ii) SOD is a challenging task due to the noisy, blurred, and less-informative image appearances of small objects. This paper proposes a new SOD dataset consisting of 39,070 images including 137,121 bird instances, which is called the Small Object Detection for Spotting Birds (SOD4SB) dataset. The detail of the challenge with the SOD4SB dataset is introduced in this paper. In total, 223 participants joined this challenge. This paper briefly introduces the award-winning methods. The dataset, the baseline code, and the website for evaluation on the public testset are publicly available.