HS-FPN: High Frequency and Spatial Perception FPN for Tiny Object Detection

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Shi, Zican, Hu, Jing, Ren, Jie, Ye, Hengkang, Yuan, Xuyang, Ouyang, Yan, He, Jia, Ji, Bo, Guo, Junyu
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912283660124160
author Shi, Zican
Hu, Jing
Ren, Jie
Ye, Hengkang
Yuan, Xuyang
Ouyang, Yan
He, Jia
Ji, Bo
Guo, Junyu
author_facet Shi, Zican
Hu, Jing
Ren, Jie
Ye, Hengkang
Yuan, Xuyang
Ouyang, Yan
He, Jia
Ji, Bo
Guo, Junyu
contents The introduction of Feature Pyramid Network (FPN) has significantly improved object detection performance. However, substantial challenges remain in detecting tiny objects, as their features occupy only a very small proportion of the feature maps. Although FPN integrates multi-scale features, it does not directly enhance or enrich the features of tiny objects. Furthermore, FPN lacks spatial perception ability. To address these issues, we propose a novel High Frequency and Spatial Perception Feature Pyramid Network (HS-FPN) with two innovative modules. First, we designed a high frequency perception module (HFP) that generates high frequency responses through high pass filters. These high frequency responses are used as mask weights from both spatial and channel perspectives to enrich and highlight the features of tiny objects in the original feature maps. Second, we developed a spatial dependency perception module (SDP) to capture the spatial dependencies that FPN lacks. Our experiments demonstrate that detectors based on HS-FPN exhibit competitive advantages over state-of-the-art models on the AI-TOD dataset for tiny object detection.
format Preprint
id arxiv_https___arxiv_org_abs_2412_10116
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle HS-FPN: High Frequency and Spatial Perception FPN for Tiny Object Detection
Shi, Zican
Hu, Jing
Ren, Jie
Ye, Hengkang
Yuan, Xuyang
Ouyang, Yan
He, Jia
Ji, Bo
Guo, Junyu
Computer Vision and Pattern Recognition
The introduction of Feature Pyramid Network (FPN) has significantly improved object detection performance. However, substantial challenges remain in detecting tiny objects, as their features occupy only a very small proportion of the feature maps. Although FPN integrates multi-scale features, it does not directly enhance or enrich the features of tiny objects. Furthermore, FPN lacks spatial perception ability. To address these issues, we propose a novel High Frequency and Spatial Perception Feature Pyramid Network (HS-FPN) with two innovative modules. First, we designed a high frequency perception module (HFP) that generates high frequency responses through high pass filters. These high frequency responses are used as mask weights from both spatial and channel perspectives to enrich and highlight the features of tiny objects in the original feature maps. Second, we developed a spatial dependency perception module (SDP) to capture the spatial dependencies that FPN lacks. Our experiments demonstrate that detectors based on HS-FPN exhibit competitive advantages over state-of-the-art models on the AI-TOD dataset for tiny object detection.
title HS-FPN: High Frequency and Spatial Perception FPN for Tiny Object Detection
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2412.10116