Small Object Detection

Small Object Detection is a computer vision task that involves detecting and localizing small objects in images or videos. This task is challenging due to the small size and low resolution of the objects, as well as other factors such as occlusion, background clutter, and variations in lighting conditions.

( Image credit: Feature-Fused SSD )

Papers

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 101–110 of 152 papers

Title	Date	Tasks	Status	Hype
Prescriptive and Descriptive Approaches to Machine-Learning Transparency	Apr 27, 2022	BIG-bench Machine LearningDescriptive	—Unverified	0
Focus-and-Detect: A Small Object Detection Framework for Aerial Images	Mar 24, 2022	Objectobject-detection	—Unverified	0
Evaluation of YOLO Models with Sliced Inference for Small Object Detection	Mar 9, 2022	Objectobject-detection	—Unverified	0
Colonoscopy polyp detection with massive endoscopic images	Feb 17, 2022	object-detectionObject Detection	—Unverified	0
Slicing Aided Hyper Inference and Fine-tuning for Small Object Detection	Feb 14, 2022	Objectobject-detection	CodeCode Available	5
Small Object Detection using Deep Learning	Jan 10, 2022	Deep LearningObject	—Unverified	0
YOLO-Z: Improving small object detection in YOLOv5 for autonomous vehicles	Dec 22, 2021	Autonomous RacingAutonomous Vehicles	CodeCode Available	1
Anchor Retouching via Model Interaction for Robust Object Detection in Aerial Images	Dec 13, 2021	Objectobject-detection	CodeCode Available	1
Remote Sensing Image Super-resolution and Object Detection: Benchmark and State of the Art	Nov 5, 2021	Generative Adversarial NetworkImage Super-Resolution	—Unverified	0
A Normalized Gaussian Wasserstein Distance for Tiny Object Detection	Oct 26, 2021	Objectobject-detection	CodeCode Available	1

Show:10 25 50

← PrevPage 11 of 16Next →

All datasets SOD4SB Private Test SOD4SB Public Test Bee4Exp Honeybee Detection SODA-D

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	Weighted Box Fusion (WBF)	AP50	30.3	—	Unverified
2	GFL + Test Time Augmentation	AP50	23.7	—	Unverified
3	DL method (YOLOv8 + Ensamble)	AP50	22.9	—	Unverified
4	Swin Transformer + Hierarchical design	AP50	22.6	—	Unverified
5	E2 method (Normalized Gaussian Wasserstein Distance + Switch Hard Augmentation + Multi scale train + Weight Moving Average + CenterNet + VarifocalNet)	AP50	22.1	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Weighted Box Fusion (WBF)	AP50	77.6	—	Unverified
2	DL method (YOLOv8 + Ensamble)	AP50	73.1	—	Unverified
3	GFL + Test Time Augmentation	AP50	73.1	—	Unverified
4	Swin Transformer + Hierarchical design	AP50	70.2	—	Unverified
5	E2 method (Normalized Gaussian Wasserstein Distance + Switch Hard Augmentation + Multi scale train + Weight Moving Average + CenterNet + VarifocalNet)	AP50	69.6	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	BeeDetector	Average F1	0.86	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	CFINet	mAP@0.5:0.95	30.7	—	Unverified