Extended Feature Pyramid Network for Small Object Detection

Small object detection remains an unsolved challenge because it is hard to extract the information of small objects with only a few pixels. While scale-level corresponding detection in feature pyramid network alleviates this problem, we find feature coupling of various scales still impairs the perfo...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on multimedia Vol. 24; pp. 1968 - 1979
Main Authors: Deng, Chunfang, Wang, Mengmeng, Liu, Liang, Liu, Yong, Jiang, Yunliang
Format: Journal Article
Language:English
Published: Piscataway IEEE 2022
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:
Datasets
deep learning
Detectors
Distillation
Feature extraction
feature pyramid
feature super-resolution
knowledge distillation
Object detection
Object recognition
Pipelines
Semantics
Signal resolution
Small object detection
Superresolution
ISSN:1520-9210, 1941-0077
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Small object detection remains an unsolved challenge because it is hard to extract the information of small objects with only a few pixels. While scale-level corresponding detection in feature pyramid network alleviates this problem, we find feature coupling of various scales still impairs the performance of small objects. In this paper, we propose an extended feature pyramid network (EFPN) with an extra high-resolution pyramid level specialized for small object detection. Specifically, we design a novel module, named feature texture transfer (FTT), which is used to super-resolve features and extract credible regional details simultaneously. Moreover, we introduce a cross resolution distillation mechanism to transfer the ability of perceiving details across the scales of the network, where a foreground-background-balanced loss function is designed to alleviate area imbalance of foreground and background. In our experiments, the proposed EFPN is efficient on both computation and memory, and yields state-of-the-art results on small traffic-sign dataset Tsinghua-Tencent 100 K and small category of general object detection dataset MS COCO.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1520-9210
1941-0077
DOI:10.1109/TMM.2021.3074273