Home Research Papers Datasets State of the Art Pricing

Discover, visualize, and connect AI research papers. Explore the latest trends and insights in artificial intelligence research.

Product

Home
Research Papers
Datasets
State of the Art

Support

Contact
Pricing
Terms of Service
Privacy Policy
About

© 2026 Papersgraph. All rights reserved.

object-detection

Small Object Detection

3260 papers • 126 benchmarks • 313 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 )

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in object-detection

Trend

Dataset

Best Model

Actions

SOD4SB Private Test

SOD4SB Private Test

SOD4SB Public Test

SOD4SB Public Test

Libraries

i

Use these libraries to find object-detection models and implementations

Datasets

No datasets available.

Subtasks

Rice Grain Disease Detection

Most implemented papers

An Energy and GPU-Computation Efficient Backbone Network for Real-Time Object Detection

Youngwan Lee, Jongyoul Park, Joong-won Hwang, Sangrok Lee, Yuseok Bae•Sun Apr 21 2019

VoVNet also outperforms widely used ResNet backbone with faster speed and better energy efficiency and the small object detection performance has been significantly improved over DenseNet and ResNet.

456

Content

Introduction Benchmarks Datasets Subtasks Libraries Papers

Bee4Exp Honeybee Detection

Bee4Exp Honeybee Detection

SODA-D

SODA-D

0

Small-Object Detection in Remote Sensing Images with End-to-End Edge-Enhanced GAN and Object Detector Network

Nilanjan Ray, Jakaria Rabbi, Matthias Schubert, Subir Chowdhury, D. Chao•Thu Mar 19 2020

This work proposed an architecture with three components: ESRGAN, EEN, and Detection network, and used different detector networks in an end-to-end manner where detector loss was backpropagated into the EESRGAN to improve the detection performance.

273 0

Slicing Aided Hyper Inference and Fine-Tuning for Small Object Detection

F. C. Akyon, S. Altinuc, A. Temi̇zel•Sun Feb 13 2022

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, and is integrated with Detectron2, MMDetection and YOLOv5 models.

353 0

Augmentation for small object detection

Z. Wojna, Kyunghyun Cho, Mate Kisantal, Jakub Murawski, Jacek Naruniec•Mon Feb 18 2019

This work analyzes the current state-of-the-art model, Mask-RCNN, on a challenging dataset, MS COCO, and shows that the overlap between small ground-truth objects and the predicted anchors is much lower than the expected IoU threshold.

631 0

Small Object Detection via Pixel Level Balancing With Applications to Blood Cell Detection

Minglei Tong, Pengzhi Chu, B. Hu, Yang Liu, Qingjie Kong•Thu Jun 16 2022

A method called pixel level balancing (PLB), which takes into account the number of pixels contained in the detection box as an impact factor to characterize the size of the inspected objects, and uses this as animpact factor to improve the accuracy of small object detection.

12 0

Real-time gun detection in CCTV: An open problem

Luis Miguel Soria-Morillo, Juan Antonio Álvarez-García, José-Joel González-Barbosa, Carlos Zaccaro, Fernando Sancho-Caparrini•Wed Sep 16 2020

A new dataset obtained from a real CCTV installed in a university and the generation of synthetic images are presented, resulting in a weapon detection model able to be used in quasi real-time CCTV improving the state of the art on weapon detection in a two stages training.

102 0

Occupancy-MAE: Self-Supervised Pre-Training Large-Scale LiDAR Point Clouds With Masked Occupancy Autoencoders

Dawei Zhao, Chen Min, Xinli Xu, Liang Xiao, Yiming Nie, B. Dai•Sun Jun 19 2022

This work proposes a solution to reduce the dependence on labelled 3D training data by leveraging pre-training on large-scale unlabeled outdoor LiDAR point clouds using masked autoencoders (MAE), specifically designed for voxel-based large-scale outdoor LiDAR point clouds.

70 0

Rethinking Rotated Object Detection with Gaussian Wasserstein Distance Loss

Qi Tian, Xue Yang, Junchi Yan, Wentao Wang, Qi Ming, Xiaopeng Zhang•Wed Jan 27 2021

The rotated bounding box is converted to a 2-D Gaussian distribution, which enables to approximate the indifferentiable rotational IoU induced loss by the Gaussian Wasserstein distance which can be learned efficiently by gradient back-propagation.

539 0

YOLO-Z: Improving small object detection in YOLOv5 for autonomous vehicles

Fabio Cuzzolin, Andrew Bradley, Aduen Benjumea, Izzedin Teeti•Tue Dec 21 2021

This study explores how the popular YOLOv5 object detector can be modified to improve its performance in detecting smaller objects, with a particular application in autonomous racing.

185 0

A Normalized Gaussian Wasserstein Distance for Tiny Object Detection

Wen Yang, Jinwang Wang, Lei Yu, Chang Xu•Mon Oct 25 2021

This work first model the bounding boxes as 2D Gaussian distributions and then proposes a new metric dubbed Normalized Wasserstein Distance (NWD), which can be easily embedded into the assignment, non-maximum suppression, and loss function of any anchor-based detector to replace the commonly used IoU metric.

485 0

Adding a benchmark result helps the community track progress.

Small Object Detection | State-of-the-Art