ESOD: Efficient Small Object Detection on High-Resolution Images

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Liu, Kai, Fu, Zhihang, Jin, Sheng, Chen, Ze, Zhou, Fan, Jiang, Rongxin, Chen, Yaowu, Ye, Jieping
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910748505014272
author Liu, Kai
Fu, Zhihang
Jin, Sheng
Chen, Ze
Zhou, Fan
Jiang, Rongxin
Chen, Yaowu
Ye, Jieping
author_facet Liu, Kai
Fu, Zhihang
Jin, Sheng
Chen, Ze
Zhou, Fan
Jiang, Rongxin
Chen, Yaowu
Ye, Jieping
contents Enlarging input images is a straightforward and effective approach to promote small object detection. However, simple image enlargement is significantly expensive on both computations and GPU memory. In fact, small objects are usually sparsely distributed and locally clustered. Therefore, massive feature extraction computations are wasted on the non-target background area of images. Recent works have tried to pick out target-containing regions using an extra network and perform conventional object detection, but the newly introduced computation limits their final performance. In this paper, we propose to reuse the detector's backbone to conduct feature-level object-seeking and patch-slicing, which can avoid redundant feature extraction and reduce the computation cost. Incorporating a sparse detection head, we are able to detect small objects on high-resolution inputs (e.g., 1080P or larger) for superior performance. The resulting Efficient Small Object Detection (ESOD) approach is a generic framework, which can be applied to both CNN- and ViT-based detectors to save the computation and GPU memory costs. Extensive experiments demonstrate the efficacy and efficiency of our method. In particular, our method consistently surpasses the SOTA detectors by a large margin (e.g., 8% gains on AP) on the representative VisDrone, UAVDT, and TinyPerson datasets. Code is available at https://github.com/alibaba/esod.
format Preprint
id arxiv_https___arxiv_org_abs_2407_16424
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle ESOD: Efficient Small Object Detection on High-Resolution Images
Liu, Kai
Fu, Zhihang
Jin, Sheng
Chen, Ze
Zhou, Fan
Jiang, Rongxin
Chen, Yaowu
Ye, Jieping
Computer Vision and Pattern Recognition
Enlarging input images is a straightforward and effective approach to promote small object detection. However, simple image enlargement is significantly expensive on both computations and GPU memory. In fact, small objects are usually sparsely distributed and locally clustered. Therefore, massive feature extraction computations are wasted on the non-target background area of images. Recent works have tried to pick out target-containing regions using an extra network and perform conventional object detection, but the newly introduced computation limits their final performance. In this paper, we propose to reuse the detector's backbone to conduct feature-level object-seeking and patch-slicing, which can avoid redundant feature extraction and reduce the computation cost. Incorporating a sparse detection head, we are able to detect small objects on high-resolution inputs (e.g., 1080P or larger) for superior performance. The resulting Efficient Small Object Detection (ESOD) approach is a generic framework, which can be applied to both CNN- and ViT-based detectors to save the computation and GPU memory costs. Extensive experiments demonstrate the efficacy and efficiency of our method. In particular, our method consistently surpasses the SOTA detectors by a large margin (e.g., 8% gains on AP) on the representative VisDrone, UAVDT, and TinyPerson datasets. Code is available at https://github.com/alibaba/esod.
title ESOD: Efficient Small Object Detection on High-Resolution Images
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2407.16424