# SlimYOLOv3: Narrower, Faster and Better for Real-Time UAV Applications

arXiv: https://arxiv.org/abs/1907.11093 · HTML: https://mlsanity.com/paper/1907.11093/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Jul 2019.

## Built on by (most cited first, 21 of 21)

- [QueryDet: Cascaded Sparse Query for Accelerating High-Resolution Small Object Detection](https://mlsanity.com/paper/2103.09136/) (2021)
- [Adaptive Sparse Convolutional Networks with Global Context Enhancement for Faster Object Detection on Drone Images](https://mlsanity.com/paper/2303.14488/) (2023)
- [Deep Learning for UAV-based Object Detection and Tracking: A Survey](https://mlsanity.com/paper/2110.12638/) (2021)
- [FBRT-YOLO: Faster and Better for Real-Time Aerial Image Detection](https://mlsanity.com/paper/2504.20670/) (2025)
- [A Deep Learning Based Automatic Defect Analysis Framework for In-situ TEM Ion Irradiations](https://mlsanity.com/paper/2108.08882/) (2021)
- [SpikeCV: Open a Continuous Computer Vision Era](https://mlsanity.com/paper/2303.11684/) (2023)
- [Compacting Deep Neural Networks for Internet of Things: Methods and Applications](https://mlsanity.com/paper/2103.11083/) (2021)
- [Real-Time Multi-Modal Semantic Fusion on Unmanned Aerial Vehicles with Label Propagation for Cross-Domain Adaptation](https://mlsanity.com/paper/2210.09739/) (2022)
- [ABCP: Automatic Block-wise and Channel-wise Network Pruning via Joint Search](https://mlsanity.com/paper/2110.03858/) (2021)
- [E3-UAV: An Edge-based Energy-Efficient Object Detection System for Unmanned Aerial Vehicles](https://mlsanity.com/paper/2308.04774/) (2023)
- [Iterative Filter Pruning for Concatenation-based CNN Architectures](https://mlsanity.com/paper/2405.03715/) (2024)
- [FasterX: Real-Time Object Detection Based on Edge GPUs for UAV Applications](https://mlsanity.com/paper/2209.03157/) (2022)
- [Deep Learning-Based Object Detection in Maritime Unmanned Aerial Vehicle Imagery: Review and Experimental Comparisons](https://mlsanity.com/paper/2311.07955/) (2023)
- [Centerness-based Instance-aware Knowledge Distillation with Task-wise Mutual Lifting for Object Detection on Drone Imagery](https://mlsanity.com/paper/2411.02861/) (2024)
- [QYOLO: Lightweight Object Detection via Quantum Inspired Shared Channel Mixing](https://mlsanity.com/paper/2604.26435/) (2026)
- [Real-Time Multi-Modal Semantic Fusion on Unmanned Aerial Vehicles](https://mlsanity.com/paper/2108.06608/) (2021)
- [Analysis and Adaptation of YOLOv4 for Object Detection in Aerial Images](https://mlsanity.com/paper/2203.10194/) (2022)
- [A lightweight and accurate YOLO-like network for small target detection in Aerial Imagery](https://mlsanity.com/paper/2204.02325/) (2022)
- [IDMS: Instance Depth for Multi-scale Monocular 3D Object Detection](https://mlsanity.com/paper/2212.01528/) (2022)
- [Real-Time Object Detection in Occluded Environment with Background Cluttering Effects Using Deep Learning](https://mlsanity.com/paper/2401.00986/) (2024)
- [Hierarchical Dual-Change Collaborative Learning for UAV Scene Change Captioning](https://mlsanity.com/paper/2603.12832/) (2026)

## Abstract (arXiv)

Drones or general Unmanned Aerial Vehicles (UAVs), endowed with computer vision function by on-board cameras and embedded systems, have become popular in a wide range of applications. However, real-time scene parsing through object detection running on a UAV platform is very challenging, due to limited memory and computing power of embedded devices. To deal with these challenges, in this paper we propose to learn efficient deep object detectors through channel pruning of convolutional layers. To this end, we enforce channel-level sparsity of convolutional layers by imposing L1 regularization on channel scaling factors and prune less informative feature channels to obtain "slim" object detectors. Based on such approach, we present SlimYOLOv3 with fewer trainable parameters and floating point operations (FLOPs) in comparison of original YOLOv3 (Joseph Redmon et al., 2018) as a promising solution for real-time object detection on UAVs. We evaluate SlimYOLOv3 on VisDrone2018-Det benchmark dataset; compelling results are achieved by SlimYOLOv3 in comparison of unpruned counterpart, including ~90.8% decrease of FLOPs, ~92.0% decline of parameter size, running ~2 times faster and comparable detection accuracy as YOLOv3. Experimental results with different pruning ratios consistently verify that proposed SlimYOLOv3 with narrower structure are more efficient, faster and better than YOLOv3, and thus are more suitable for real-time object detection on UAVs. Our codes are made publicly available at https://github.com/PengyiZhang/SlimYOLOv3.