YOLC: You Only Look Clusters for Tiny Object Detection in Aerial Images

TL;DR

YOLC introduces a cluster-based, anchor-free detection framework with adaptive zooming and advanced loss functions, significantly improving tiny object detection in large aerial images.

Contribution

The paper presents YOLC, a novel framework combining cluster-based adaptive zooming, Gaussian Wasserstein loss, and deformable convolutions for enhanced tiny object detection in aerial imagery.

Findings

Outperforms existing methods on Visdrone2019 and UAVDT datasets.

Effectively detects small objects with high accuracy.

Reduces computational waste through non-uniform object distribution handling.

Abstract

Detecting objects from aerial images poses significant challenges due to the following factors: 1) Aerial images typically have very large sizes, generally with millions or even hundreds of millions of pixels, while computational resources are limited. 2) Small object size leads to insufficient information for effective detection. 3) Non-uniform object distribution leads to computational resource wastage. To address these issues, we propose YOLC (You Only Look Clusters), an efficient and effective framework that builds on an anchor-free object detector, CenterNet. To overcome the challenges posed by large-scale images and non-uniform object distribution, we introduce a Local Scale Module (LSM) that adaptively searches cluster regions for zooming in for accurate detection. Additionally, we modify the regression loss using Gaussian Wasserstein distance (GWD) to obtain high-quality bounding boxes. Deformable convolution and refinement methods are employed in the detection head to enhance the detection of small objects. We perform extensive experiments on two aerial image datasets, including Visdrone2019 and UAVDT, to demonstrate the effectiveness and superiority of our proposed approach. Code is available at https://github.com/dawn-ech/YOLC.