Towards Large-Scale Small Object Detection: Survey and Benchmarks

Abstract

With the rise of deep convolutional neural networks, object detection has achieved prominent advances in past years. However, such prosperity could not camouflage the unsatisfactory situation of Small Object Detection (SOD), one of the notoriously challenging tasks in computer vision, owing to the poor visual appearance and noisy representation caused by the intrinsic structure of small targets. In addition, large-scale dataset for benchmarking small object detection methods remains a bottleneck. In this paper, we first conduct a thorough review of small object detection. Then, to catalyze the development of SOD, we construct two large-scale Small Object Detection dAtasets (SODA), SODA-D and SODA-A, which focus on the Driving and Aerial scenarios respectively. SODA-D includes 24828 high-quality traffic images and 278433 instances of nine categories. For SODA-A, we harvest 2513 high resolution aerial images and annotate 872069 instances over nine classes. The proposed datasets, as we know, are the first-ever attempt to large-scale benchmarks with a vast collection of exhaustively annotated instances tailored for multi-category SOD. Finally, we evaluate the performance of mainstream methods on SODA. We expect the released benchmarks could facilitate the development of SOD and spawn more breakthroughs in this field. Datasets and codes are available at: \url{https://shaunyuan22.github.io/SODA}.

in IEEE Transactions on Pattern Analysis and Machine Intelligence (2023)

References in corpus (14)

• YOLOX: Exceeding YOLO Series in 2021
• DSSD : Deconvolutional Single Shot Detector
• A Simple Way to Initialize Recurrent Networks of Rectified Linear Units
• Learning Spatial Fusion for Single-Shot Object Detection
• Anchor-free Oriented Proposal Generator for Object Detection
• Detecting tiny objects in aerial images: A normalized Wasserstein distance and a new benchmark
• MMRotate: A Rotated Object Detection Benchmark using PyTorch
• R${}^2$-CNN: Fast Tiny Object Detection in Large-Scale Remote Sensing Images
• Face Attention Network: An Effective Face Detector for the Occluded Faces
• Focus-and-Detect: A Small Object Detection Framework for Aerial Images
• TJU-DHD: A Diverse High-Resolution Dataset for Object Detection
• SODA10M: A Large-Scale 2D Self/Semi-Supervised Object Detection Dataset for Autonomous Driving
• Intrinsic Relationship Reasoning for Small Object Detection
• AdaZoom: Adaptive Zoom Network for Multi-Scale Object Detection in Large Scenes

Cited by in corpus (14)

• Small Object Detection: A Comprehensive Survey on Challenges, Techniques and Real-World Applications
• Predicting Gradient is Better: Exploring Self-Supervised Learning for SAR ATR with a Joint-Embedding Predictive Architecture
• Oriented object detection in optical remote sensing images using deep learning: a survey
• Highly Efficient and Unsupervised Framework for Moving Object Detection in Satellite Videos
• SpecDETR: A transformer-based hyperspectral point object detection network
• DPNet: Dynamic Pooling Network for Tiny Object Detection
• DSORT-MCU: Detecting Small Objects in Real-Time on Microcontroller Units
• VME: A Satellite Imagery Dataset and Benchmark for Detecting Vehicles in the Middle East and Beyond
• ImageRAG: Enhancing Ultra High Resolution Remote Sensing Imagery Analysis with ImageRAG
• Prompt-Driven Building Footprint Extraction in Aerial Images with Offset-Building Model
• Renormalized Connection for Scale-preferred Object Detection in Satellite Imagery
• Adaptive Modality Balanced Online Knowledge Distillation for Brain-Eye-Computer based Dim Object Detection
• LED: A Benchmark for Evaluating Layout Error Detection in Document Analysis
• Self-Supervised Learning for Real-World Object Detection: a Survey