Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Jul 25, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

Towards Large-Scale Small Object Detection: Survey and Benchmarks.

Gong Cheng, Xiang Yuan, Xiwen Yao

IEEE Transactions on Pattern Analysis and Machine Intelligence

|June 29, 2023

Summary

This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Interactions Between Commensal Microbes and Mosquito-Borne Viruses.

Annual review of virology·2025

Same author

STDatav2: Accessing Efficient Black-Box Stealing for Adversarial Attacks.

IEEE transactions on pattern analysis and machine intelligence·2025

Same author

Deciphering the senescence-based tumoral heterogeneity and characteristics in pancreatic cancer: Results from parallel bulk and single-cell transcriptome data.

IUBMB life·2025

Same author

Erucic acid promotes intramuscular fat deposition through the PPARγ-FABP4/CD36 pathway.

International journal of biological macromolecules·2025

Same author

A predictive language model for SARS-CoV-2 evolution.

Signal transduction and targeted therapy·2024

Same author

The Applications of Plant Polyphenols: Implications for the Development and Biotechnological Utilization of <i>Ilex</i> Species.

Plants (Basel, Switzerland)·2024

Same journal

TraGraph-GS: Trajectory Graph-based Gaussian Splatting for Arbitrary Large-Scale Scene Rendering.

IEEE transactions on pattern analysis and machine intelligence·2026

Same journal

SWIFT: A Small-World Interaction Framework for Flow-Aware Trajectory Prediction in Autonomous Driving.

IEEE transactions on pattern analysis and machine intelligence·2026

Same journal

HardFlow: Hard-Constrained Sampling for Flow-Matching Models Via Trajectory Optimization.

IEEE transactions on pattern analysis and machine intelligence·2026

Same journal

Industrial Brain: Self-Evolving Neuro-Symbolic Autonomy with Causal Resilience for Cyber-Physical Systems.

IEEE transactions on pattern analysis and machine intelligence·2026

Same journal

Adaptive Hardness-Driven Dictionary Distillation for Incomplete Streaming View Clustering.

IEEE transactions on pattern analysis and machine intelligence·2026

Same journal

Mixture of Global and Local Experts with Diffusion Transformer for Controllable Face Generation.

IEEE transactions on pattern analysis and machine intelligence·2026

See all related articles

This study addresses the challenges in small object detection (SOD) by introducing two large-scale datasets, SODA-D and SODA-A. These benchmarks aim to advance computer vision research in this difficult area.

Area of Science:

Computer Vision
Machine Learning
Artificial Intelligence

Background:

Deep convolutional neural networks have advanced object detection, but small object detection (SOD) remains challenging due to target appearance and representation issues.
A lack of large-scale datasets hinders the development and benchmarking of SOD methods.

Purpose of the Study:

To conduct a comprehensive review of existing small object detection techniques.
To introduce two novel, large-scale datasets, SODA-D and SODA-A, specifically designed for benchmarking multi-category small object detection.

Main Methods:

A thorough literature review of small object detection methods was performed.
Two extensive datasets, SODA-D (driving scenarios) and SODA-A (aerial scenarios), were constructed with detailed annotations.

More Related Videos

Methods to Test Visual Attention Online

Methods to Test Visual Attention Online

Published on: February 19, 2015

Investigating Object Representations in the Macaque Dorsal Visual Stream Using Single-unit Recordings

Investigating Object Representations in the Macaque Dorsal Visual Stream Using Single-unit Recordings

Published on: August 1, 2018

Related Experiment Videos

Last Updated: Jul 25, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

Methods to Test Visual Attention Online

Methods to Test Visual Attention Online

Published on: February 19, 2015

Investigating Object Representations in the Macaque Dorsal Visual Stream Using Single-unit Recordings

Investigating Object Representations in the Macaque Dorsal Visual Stream Using Single-unit Recordings

Published on: August 1, 2018

Performance evaluation of mainstream SOD methods on the newly created SODA datasets.

Main Results:

SODA-D comprises 24,828 traffic images with 278,433 instances across nine categories.
SODA-A contains 2,513 high-resolution aerial images with 872,069 instances across nine classes.
These datasets represent the first large-scale benchmarks with exhaustive annotations for multi-category SOD.

Conclusions:

The newly introduced SODA datasets are expected to significantly catalyze progress in small object detection research.
These benchmarks will facilitate the evaluation of current methods and encourage further breakthroughs in the field of computer vision.