# Speed/accuracy trade-offs for modern convolutional object detectors

arXiv: https://arxiv.org/abs/1611.10012 · HTML: https://mlsanity.com/paper/1611.10012/

## Key facts

- Cited by 198 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Nov 2016.

## Built on by (most cited first, 30 of 198)

- [Object Detection in Aerial Images: A Large-Scale Benchmark and Challenges](https://mlsanity.com/paper/2102.12219/) (2021)
- [FAIR1M: A Benchmark Dataset for Fine-grained Object Recognition in High-Resolution Remote Sensing Imagery](https://mlsanity.com/paper/2103.05569/) (2021)
- [Towards Large-Scale Small Object Detection: Survey and Benchmarks](https://mlsanity.com/paper/2207.14096/) (2022)
- [Distilling Object Detectors via Decoupled Features](https://mlsanity.com/paper/2103.14475/) (2021)
- [CBNet: A Composite Backbone Network Architecture for Object Detection](https://mlsanity.com/paper/2107.00420/) (2021)
- [3D Object Detection from Images for Autonomous Driving: A Survey](https://mlsanity.com/paper/2202.02980/) (2022)
- [Multi-Modal 3D Object Detection in Autonomous Driving: a Survey](https://mlsanity.com/paper/2106.12735/) (2021)
- [DTA: Physical Camouflage Attacks using Differentiable Transformation Network](https://mlsanity.com/paper/2203.09831/) (2022)
- [Visual Object Tracking with Discriminative Filters and Siamese Networks: A Survey and Outlook](https://mlsanity.com/paper/2112.02838/) (2021)
- [Tracking Pedestrian Heads in Dense Crowd](https://mlsanity.com/paper/2103.13516/) (2021)
- [Structural Pruning via Latency-Saliency Knapsack](https://mlsanity.com/paper/2210.06659/) (2022)
- [Do better ImageNet classifiers assess perceptual similarity better?](https://mlsanity.com/paper/2203.04946/) (2022)
- [Pylot: A Modular Platform for Exploring Latency-Accuracy Tradeoffs in Autonomous Vehicles](https://mlsanity.com/paper/2104.07830/) (2021)
- [ACTIVE: Towards Highly Transferable 3D Physical Camouflage for Universal and Robust Vehicle Evasion](https://mlsanity.com/paper/2308.07009/) (2023)
- [Simple Training Strategies and Model Scaling for Object Detection](https://mlsanity.com/paper/2107.00057/) (2021)
- [On the Connection between Pre-training Data Diversity and Fine-tuning Robustness](https://mlsanity.com/paper/2307.12532/) (2023)
- [A Survey on Collaborative DNN Inference for Edge Intelligence](https://mlsanity.com/paper/2207.07812/) (2022)
- [The Caltech Fish Counting Dataset: A Benchmark for Multiple-Object Tracking and Counting](https://mlsanity.com/paper/2207.09295/) (2022)
- [LEOD: Label-Efficient Object Detection for Event Cameras](https://mlsanity.com/paper/2311.17286/) (2023)
- [Sylph: A Hypernetwork Framework for Incremental Few-shot Object Detection](https://mlsanity.com/paper/2203.13903/) (2022)
- [ROADWork: A Dataset and Benchmark for Learning to Recognize, Observe, Analyze and Drive Through Work Zones](https://mlsanity.com/paper/2406.07661/) (2024)
- [Biased Mixtures Of Experts: Enabling Computer Vision Inference Under Data Transfer Limitations](https://mlsanity.com/paper/2008.09662/) (2020)
- [Proper Reuse of Image Classification Features Improves Object Detection](https://mlsanity.com/paper/2204.00484/) (2022)
- [Does Robustness on ImageNet Transfer to Downstream Tasks?](https://mlsanity.com/paper/2204.03934/) (2022)
- [End-to-End Spatio-Temporal Action Localisation with Video Transformers](https://mlsanity.com/paper/2304.12160/) (2023)
- [Dogfight: Detecting Drones from Drones Videos](https://mlsanity.com/paper/2103.17242/) (2021)
- [Fine-grained Controllable Video Generation via Object Appearance and Context](https://mlsanity.com/paper/2312.02919/) (2023)
- [YORO -- Lightweight End to End Visual Grounding](https://mlsanity.com/paper/2211.07912/) (2022)
- [Unveiling Energy Efficiency in Deep Learning: Measurement, Prediction, and Scoring across Edge Devices](https://mlsanity.com/paper/2310.18329/) (2023)
- [A Comprehensive Survey of Convolutions in Deep Learning: Applications, Challenges, and Future Trends](https://mlsanity.com/paper/2402.15490/) (2024)

## Abstract (arXiv)

The goal of this paper is to serve as a guide for selecting a detection architecture that achieves the right speed/memory/accuracy balance for a given application and platform. To this end, we investigate various ways to trade accuracy for speed and memory usage in modern convolutional object detection systems. A number of successful systems have been proposed in recent years, but apples-to-apples comparisons are difficult due to different base feature extractors (e.g., VGG, Residual Networks), different default image resolutions, as well as different hardware and software platforms. We present a unified implementation of the Faster R-CNN [Ren et al., 2015], R-FCN [Dai et al., 2016] and SSD [Liu et al., 2015] systems, which we view as "meta-architectures" and trace out the speed/accuracy trade-off curve created by using alternative feature extractors and varying other critical parameters such as image size within each of these meta-architectures. On one extreme end of this spectrum where speed and memory are critical, we present a detector that achieves real time speeds and can be deployed on a mobile device. On the opposite end in which accuracy is critical, we present a detector that achieves state-of-the-art performance measured on the COCO detection task.