# AdaScale: Towards Real-time Video Object Detection Using Adaptive Scaling

arXiv: https://arxiv.org/abs/1902.02910 · HTML: https://mlsanity.com/paper/1902.02910/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Feb 2019.

## Built on by (most cited first, 27 of 27)

- [TransVOD: End-to-End Video Object Detection with Spatial-Temporal Transformers](https://mlsanity.com/paper/2201.05047/) (2022)
- [Real-time Object Detection for Streaming Perception](https://mlsanity.com/paper/2203.12338/) (2022)
- [Enabling Design Methodologies and Future Trends for Edge AI: Specialization and Co-design](https://mlsanity.com/paper/2103.15750/) (2021)
- [DAMO-StreamNet: Optimizing Streaming Perception in Autonomous Driving](https://mlsanity.com/paper/2303.17144/) (2023)
- [Eventful Transformers: Leveraging Temporal Redundancy in Vision Transformers](https://mlsanity.com/paper/2308.13494/) (2023)
- [LongShortNet: Exploring Temporal and Semantic Features Fusion in Streaming Perception](https://mlsanity.com/paper/2210.15518/) (2022)
- [StreamYOLO: Real-time Object Detection for Streaming Perception](https://mlsanity.com/paper/2207.10433/) (2022)
- [Instance-Warp: Saliency Guided Image Warping for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2403.12712/) (2024)
- [Survey: Exploiting Data Redundancy for Optimization of Deep Learning](https://mlsanity.com/paper/2208.13363/) (2022)
- [Data-Efficient Training of CNNs and Transformers with Coresets: A Stability Perspective](https://mlsanity.com/paper/2303.02095/) (2023)
- [Chanakya: Learning Runtime Decisions for Adaptive Real-Time Perception](https://mlsanity.com/paper/2106.05665/) (2021)
- [Event Neural Networks](https://mlsanity.com/paper/2112.00891/) (2021)
- [DeepScale: Online Frame Size Adaptation for Multi-object Tracking on Smart Cameras and Edge Servers](https://mlsanity.com/paper/2107.10404/) (2021)
- [Towards 3D Object Detection with 2D Supervision](https://mlsanity.com/paper/2211.08287/) (2022)
- [Learned Two-Plane Perspective Prior based Image Resampling for Efficient Object Detection](https://mlsanity.com/paper/2303.14311/) (2023)
- [Panopticus: Omnidirectional 3D Object Detection on Resource-constrained Edge Devices](https://mlsanity.com/paper/2410.01270/) (2024)
- [Do You See What I See? Capabilities and Limits of Automated Multimedia Content Analysis](https://mlsanity.com/paper/2201.11105/) (2021)
- [OneAdapt: Fast Configuration Adaptation for Video Analytics Applications via Backpropagation](https://mlsanity.com/paper/2310.02422/) (2023)
- [AttTrack: Online Deep Attention Transfer for Multi-object Tracking](https://mlsanity.com/paper/2210.08648/) (2022)
- [DANCE: DAta-Network Co-optimization for Efficient Segmentation Model Training and Inference](https://mlsanity.com/paper/2107.07706/) (2021)
- [Virtuoso: Video-based Intelligence for real-time tuning on SOCs](https://mlsanity.com/paper/2112.13076/) (2021)
- [Learn to Compress (LtC): Efficient Learning-based Streaming Video Analytics](https://mlsanity.com/paper/2307.12171/) (2023)
- [Mondrian: On-Device High-Performance Video Analytics with Compressive Packed Inference](https://mlsanity.com/paper/2403.07598/) (2024)
- [A Survey on Efficiency Optimization Techniques for DNN-based Video Analytics: Process Systems, Algorithms, and Applications](https://mlsanity.com/paper/2507.15628/) (2025)
- [A comprehensive overview of deep learning models for object detection from videos/images](https://mlsanity.com/paper/2601.14677/) (2026)
- [Scale-Gest: Scalable Model-Space Synthesis and Runtime Selection for On-Device Gesture Detection](https://mlsanity.com/paper/2605.12506/) (2026)
- [On Exploring Input Resolution Scaling For Anytime LiDAR Object Detection](https://mlsanity.com/paper/2607.08391/) (2026)

## Abstract (arXiv)

In vision-enabled autonomous systems such as robots and autonomous cars, video object detection plays a crucial role, and both its speed and accuracy are important factors to provide reliable operation. The key insight we show in this paper is that speed and accuracy are not necessarily a trade-off when it comes to image scaling. Our results show that re-scaling the image to a lower resolution will sometimes produce better accuracy. Based on this observation, we propose a novel approach, dubbed AdaScale, which adaptively selects the input image scale that improves both accuracy and speed for video object detection. To this end, our results on ImageNet VID and mini YouTube-BoundingBoxes datasets demonstrate 1.3 points and 2.7 points mAP improvement with 1.6x and 1.8x speedup, respectively. Additionally, we improve state-of-the-art video acceleration work by an extra 1.25x speedup with slightly better mAP on ImageNet VID dataset.