Patch-based Selection and Refinement for Early Object Detection

TL;DR

This paper introduces a patch-based detection method using transformers and diffusion models to improve early detection of small objects, significantly increasing accuracy and reducing computational load.

Contribution

It proposes a novel patch-based, transformer-driven algorithm with diffusion models for early small object detection, enhancing accuracy and efficiency.

Findings

mAP for small objects increased from 1.03 to 8.93

reduced data volume in computation by over 77%

demonstrated on BDD100K dataset

Abstract

Early object detection (OD) is a crucial task for the safety of many dynamic systems. Current OD algorithms have limited success for small objects at a long distance. To improve the accuracy and efficiency of such a task, we propose a novel set of algorithms that divide the image into patches, select patches with objects at various scales, elaborate the details of a small object, and detect it as early as possible. Our approach is built upon a transformer-based network and integrates the diffusion model to improve the detection accuracy. As demonstrated on BDD100K, our algorithms enhance the mAP for small objects from 1.03 to 8.93, and reduce the data volume in computation by more than 77\%. The source code is available at \href{https://github.com/destiny301/dpr}{https://github.com/destiny301/dpr}