SOTAVerified

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 AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 126–150 of 152 papers

TitleStatusHype
SOD-MTGAN: Small Object Detection via Multi-Task Generative Adversarial Network—0
Spatio-temporal Tubelet Feature Aggregation and Object Linking in Videos—0
SWIPENET: Object detection in noisy underwater images—0
The Power of Tiling for Small Object Detection—0
TinyDet: Accurate Small Object Detection in Lightweight Generic Detectors—0
Towards Large-Scale Small Object Detection: Survey and Benchmarks—0
Underwater object detection using Invert Multi-Class Adaboost with deep learning—0
Video text tracking for dense and small text based on pp-yoloe-r and sort algorithm—0
XS-VID: An Extremely Small Video Object Detection Dataset—0
YOLO-LLTS: Real-Time Low-Light Traffic Sign Detection via Prior-Guided Enhancement and Multi-Branch Feature Interaction—0
YOLO-TLA: An Efficient and Lightweight Small Object Detection Model based on YOLOv5—0
YOLOv5-Based Object Detection for Emergency Response in Aerial Imagery—0
MDSSD: Multi-scale Deconvolutional Single Shot Detector for Small ObjectsCode0
Small Object Detection via Pixel Level Balancing With Applications to Blood Cell DetectionCode0
IDD-YOLOv5: A Lightweight Insulator Defect Real-time Detection AlgorithmCode0
Feature-Fused SSD: Fast Detection for Small ObjectsCode0
1st Place Solutions of Waymo Open Dataset Challenge 2020 -- 2D Object Detection TrackCode0
Sense Less, Generate More: Pre-training LiDAR Perception with Masked Autoencoders for Ultra-Efficient 3D SensingCode0
Dr^2Net: Dynamic Reversible Dual-Residual Networks for Memory-Efficient FinetuningCode0
Select-Mosaic: Data Augmentation Method for Dense Small Object ScenesCode0
Rethinking Rotated Object Detection with Gaussian Wasserstein Distance LossCode0
YOLO-Ant: A Lightweight Detector via Depthwise Separable Convolutional and Large Kernel Design for Antenna Interference Source DetectionCode0
PanSR: An Object-Centric Mask Transformer for Panoptic SegmentationCode0
Deep Learning-Based Object Detection in Maritime Unmanned Aerial Vehicle Imagery: Review and Experimental ComparisonsCode0
VME: A Satellite Imagery Dataset and Benchmark for Detecting Vehicles in the Middle East and BeyondCode0
Show:102550
← PrevPage 6 of 7Next →
All datasetsSOD4SB Private TestSOD4SB Public TestBee4Exp Honeybee DetectionSODA-D

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Weighted Box Fusion (WBF)AP5030.3—Unverified
2GFL + Test Time AugmentationAP5023.7—Unverified
3DL method (YOLOv8 + Ensamble)AP5022.9—Unverified
4Swin Transformer + Hierarchical designAP5022.6—Unverified
5E2 method (Normalized Gaussian Wasserstein Distance + Switch Hard Augmentation + Multi scale train + Weight Moving Average + CenterNet + VarifocalNet)AP5022.1—Unverified
#ModelMetricClaimedVerifiedStatus
1Weighted Box Fusion (WBF)AP5077.6—Unverified
2GFL + Test Time AugmentationAP5073.1—Unverified
3DL method (YOLOv8 + Ensamble)AP5073.1—Unverified
4Swin Transformer + Hierarchical designAP5070.2—Unverified
5E2 method (Normalized Gaussian Wasserstein Distance + Switch Hard Augmentation + Multi scale train + Weight Moving Average + CenterNet + VarifocalNet)AP5069.6—Unverified
#ModelMetricClaimedVerifiedStatus
1BeeDetectorAverage F10.86—Unverified
#ModelMetricClaimedVerifiedStatus
1CFINetmAP@0.5:0.9530.7—Unverified