# Tiny-DSOD: Lightweight Object Detection for Resource-Restricted Usages

arXiv: https://arxiv.org/abs/1807.11013 · HTML: https://mlsanity.com/paper/1807.11013/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Jul 2018.

## Built on by (most cited first, 15 of 15)

- [Distilling Object Detectors via Decoupled Features](https://mlsanity.com/paper/2103.14475/) (2021)
- [Towards Light-weight and Real-time Line Segment Detection](https://mlsanity.com/paper/2106.00186/) (2021)
- [YOLO-ReT: Towards High Accuracy Real-time Object Detection on Edge GPUs](https://mlsanity.com/paper/2110.13713/) (2021)
- [A Unified Light Framework for Real-time Fault Detection of Freight Train Images](https://mlsanity.com/paper/2102.00381/) (2021)
- [Efficient Object Detection in Optical Remote Sensing Imagery via Attention-based Feature Distillation](https://mlsanity.com/paper/2310.18676/) (2023)
- [DPNet: Dual-Path Network for Real-time Object Detection with Lightweight Attention](https://mlsanity.com/paper/2209.13933/) (2022)
- [MobileDenseNet: A new approach to object detection on mobile devices](https://mlsanity.com/paper/2207.11031/) (2022)
- [Smart Scissor: Coupling Spatial Redundancy Reduction and CNN Compression for Embedded Hardware](https://mlsanity.com/paper/2607.06915/) (2026)
- [TinyDet: Accurate Small Object Detection in Lightweight Generic Detectors](https://mlsanity.com/paper/2304.03428/) (2023)
- [DPNET: Dual-Path Network for Efficient Object Detectioj with Lightweight Self-Attention](https://mlsanity.com/paper/2111.00500/) (2021)
- [Group channel pruning and spatial attention distilling for object detection](https://mlsanity.com/paper/2306.01526/) (2023)
- [High-Speed Detector For Low-Powered Devices In Aerial Grasping](https://mlsanity.com/paper/2402.14591/) (2024)
- [Designing Object Detection Models for TinyML: Foundations, Comparative Analysis, Challenges, and Emerging Solutions](https://mlsanity.com/paper/2508.08352/) (2025)
- [CircleNet: Reciprocating Feature Adaptation for Robust Pedestrian Detection](https://mlsanity.com/paper/2212.05691/) (2022)
- [EdgeCompress: Coupling Multidimensional Model Compression and Dynamic Inference for EdgeAI](https://mlsanity.com/paper/2607.06982/) (2026)

## Abstract (arXiv)

Object detection has made great progress in the past few years along with the development of deep learning. However, most current object detection methods are resource hungry, which hinders their wide deployment to many resource restricted usages such as usages on always-on devices, battery-powered low-end devices, etc. This paper considers the resource and accuracy trade-off for resource-restricted usages during designing the whole object detection framework. Based on the deeply supervised object detection (DSOD) framework, we propose Tiny-DSOD dedicating to resource-restricted usages. Tiny-DSOD introduces two innovative and ultra-efficient architecture blocks: depthwise dense block (DDB) based backbone and depthwise feature-pyramid-network (D-FPN) based front-end. We conduct extensive experiments on three famous benchmarks (PASCAL VOC 2007, KITTI, and COCO), and compare Tiny-DSOD to the state-of-the-art ultra-efficient object detection solutions such as Tiny-YOLO, MobileNet-SSD (v1 & v2), SqueezeDet, Pelee, etc. Results show that Tiny-DSOD outperforms these solutions in all the three metrics (parameter-size, FLOPs, accuracy) in each comparison. For instance, Tiny-DSOD achieves 72.1% mAP with only 0.95M parameters and 1.06B FLOPs, which is by far the state-of-the-arts result with such a low resource requirement.