mlsanityData to 14 Oct 2026

TinyDet: Accurate Small Object Detection in Lightweight Generic Detectors

arXiv 2304.03428 ↗First posted 7 Apr 2023cs.CVcited by 2

Not on the map. Why?

Abstract (arXiv)

Small object detection requires the detection head to scan a large number of positions on image feature maps, which is extremely hard for computation- and energy-efficient lightweight generic detectors. To accurately detect small objects with limited computation, we propose a two-stage lightweight detection framework with extremely low computation complexity, termed as TinyDet. It enables high-resolution feature maps for dense anchoring to better cover small objects, proposes a sparsely-connected convolution for computation reduction, enhances the early stage features in the backbone, and addresses the feature misalignment problem for accurate small object detection. On the COCO benchmark, our TinyDet-M achieves 30.3 AP and 13.5 AP^s with only 991 MFLOPs, which is the first detector that has an AP over 30 with less than 1 GFLOPs; besides, TinyDet-S and TinyDet-L achieve promising performance under different computation limitation.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 40 of its 49 references that are in the map. First posted on arXiv 7 Apr 2023.

Builds on

40 of 49 references.

References · 40

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  3. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  4. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
  5. 2022Generative Adversarial Networkscited by 5,627
  6. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 5,045
  7. 2016Feature Pyramid Networks for Object Detectioncited by 5,036
  8. 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,795
  9. 2017Squeeze-and-Excitation Networkscited by 4,789
  10. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,845
  11. 2015SSD: Single Shot MultiBox Detectorcited by 3,130
  12. 2016Xception: Deep Learning with Depthwise Separable Convolutionscited by 2,332
28 more
  1. 2019Searching for MobileNetV3cited by 1,994
  2. 2016YOLO9000: Better, Faster, Strongercited by 1,431
  3. 2019Deep High-Resolution Representation Learning for Visual Recognitioncited by 1,420
  4. 2019MMDetection: Open MMLab Detection Toolbox and Benchmarkcited by 1,385
  5. 2017ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devicescited by 1,200
  6. 2018ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Designcited by 1,136
  7. 2021YOLOX: Exceeding YOLO Series in 2021cited by 1,071
  8. 2019EfficientDet: Scalable and Efficient Object Detectioncited by 1,020
  9. 2017Focal Loss for Dense Object Detectioncited by 752
  10. 2018ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardwarecited by 673
  11. 2016Training Region-based Object Detectors with Online Hard Example Miningcited by 579
  12. 2017Understanding the Effective Receptive Field in Deep Convolutional Neural Networkscited by 553
  13. 2018FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Searchcited by 485
  14. 2016R-FCN: Object Detection via Region-based Fully Convolutional Networkscited by 414
  15. 2017Soft-NMS -- Improving Object Detection With One Line of Codecited by 382
  16. 2019CSPNet: A New Backbone that can Enhance Learning Capability of CNNcited by 381
  17. 2019NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detectioncited by 291
  18. 2015Inside-Outside Net: Detecting Objects in Context with Skip Pooling and Recurrent Neural Networkscited by 80
  19. 2017Perceptual Generative Adversarial Networks for Small Object Detectioncited by 76
  20. 2016Finding Tiny Facescited by 72
  21. 2017MegDet: A Large Mini-Batch Object Detectorcited by 66
  22. 2018Pelee: A Real-Time Object Detection System on Mobile Devicescited by 56
  23. 2019ThunderNet: Towards Real-time Generic Object Detectioncited by 42
  24. 2017Light-Head R-CNN: In Defense of Two-Stage Object Detectorcited by 30
  25. 2018Tiny-DSOD: Lightweight Object Detection for Resource-Restricted Usagescited by 15
  26. 2017Feature-Fused SSD: Fast Detection for Small Objectscited by 14
  27. 2017Context-Aware Single-Shot Detectorcited by 4
  28. 2019RefineDetLite: A Lightweight One-stage Object Detection Framework for CPU-only Devicescited by 3

Built on by

Cited by year

Citing papers per year: 2024: 1; 2025: 1.

2 papers.

  1. 2025Designing Object Detection Models for TinyML: Foundations, Comparative Analysis, Challenges, and Emerging Solutionscited by 1
  2. 2024Improving Apple Object Detection with Occlusion-Enhanced Distillationcited by 0