Scale Match for Tiny Person Detection
Xuehui Yu, Yuqi Gong, Nan Jiang, Qixiang Ye, Zhenjun Han

TL;DR
This paper introduces the TinyPerson benchmark for tiny object detection, identifies scale mismatch as a key challenge, and proposes a Scale Match method to improve detection performance of tiny persons in complex backgrounds.
Contribution
The paper presents a new benchmark for tiny object detection and a simple scale matching technique to enhance feature representation and detection accuracy.
Findings
Significant performance improvements over state-of-the-art detectors
The scale mismatch issue impacts tiny object detection
The TinyPerson benchmark reflects real-world detection challenges
Abstract
Visual object detection has achieved unprecedented ad-vance with the rise of deep convolutional neural networks.However, detecting tiny objects (for example tiny per-sons less than 20 pixels) in large-scale images remainsnot well investigated. The extremely small objects raisea grand challenge about feature representation while themassive and complex backgrounds aggregate the risk offalse alarms. In this paper, we introduce a new benchmark,referred to as TinyPerson, opening up a promising directionfor tiny object detection in a long distance and with mas-sive backgrounds. We experimentally find that the scale mis-match between the dataset for network pre-training and thedataset for detector learning could deteriorate the featurerepresentation and the detectors. Accordingly, we proposea simple yet effective Scale Match approach to align theobject scales between the two datasets for…
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
TopicsVideo Surveillance and Tracking Methods · Advanced Neural Network Applications · Advanced Image and Video Retrieval Techniques
