Small Object Detection
42 papers with code • 4 benchmarks • 11 datasets
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 )
Benchmarks
These leaderboards are used to track progress in Small Object Detection
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
Datasets
DOTA
iSAID
RF100
SOD4SB
SODA-A
Aircraft Context Dataset
SODA-D
USC-GRAD-STDdb
Blood Cell Detection Dataset
Latest papers
Slicing Aided Hyper Inference and Fine-tuning for Small Object Detection
PaddlePaddle/PaddleDetection
•
•
In this work, an open-source framework called Slicing Aided Hyper Inference (SAHI) is proposed that provides a generic slicing aided inference and fine-tuning pipeline for small object detection.
YOLO-Z: Improving small object detection in YOLOv5 for autonomous vehicles
nqt228/YoloZ
•
•
As autonomous vehicles and autonomous racing rise in popularity, so does the need for faster and more accurate detectors.
Anchor Retouching via Model Interaction for Robust Object Detection in Aerial Images
qxgeng/dea-net
•
•
On DOTA, our DEA-Net which integrated with the baseline of RoI-Transformer surpasses the advanced method by 0. 40% mean-Average-Precision (mAP) for oriented object detection with a weaker backbone network (ResNet-101 vs ResNet-152) and 3. 08% mean-Average-Precision (mAP) for horizontal object detection with the same backbone.
A Normalized Gaussian Wasserstein Distance for Tiny Object Detection
jwwangchn/NWD
•
•
Our key observation is that Intersection over Union (IoU) based metrics such as IoU itself and its extensions are very sensitive to the location deviation of the tiny objects, and drastically deteriorate the detection performance when used in anchor-based detectors.
The Aircraft Context Dataset: Understanding and Optimizing Data Variability in Aerial Domains
Despite their increasing demand for assistant and autonomous systems, the recent shift towards data-driven approaches has hardly reached aerial domains, partly due to a lack of specific training and test data.
A Comprehensive Approach for UAV Small Object Detection with Simulation-based Transfer Learning and Adaptive Fusion
Precisely detection of Unmanned Aerial Vehicles(UAVs) plays a critical role in UAV defense systems.
FOVEA: Foveated Image Magnification for Autonomous Navigation
Efficient processing of high-res video streams is safety-critical for many robotics applications such as autonomous driving.
QueryDet: Cascaded Sparse Query for Accelerating High-Resolution Small Object Detection
ChenhongyiYang/QueryDet-PyTorch
•
•
CVPR 2022
On the popular COCO dataset, the proposed method improves the detection mAP by 1. 0 and mAP-small by 2. 0, and the high-resolution inference speed is improved to 3. 0x on average.
A Method for Detection of Small Moving Objects in UAV Videos
To circumvent this problem, we propose training a CNN using synthetic videos generated by adding small blob-like objects to video sequences with real-world backgrounds.
Rethinking Rotated Object Detection with Gaussian Wasserstein Distance Loss
Boundary discontinuity and its inconsistency to the final detection metric have been the bottleneck for rotating detection regression loss design.
