# An Energy and GPU-Computation Efficient Backbone Network for Real-Time Object Detection

arXiv: https://arxiv.org/abs/1904.09730 · HTML: https://mlsanity.com/paper/1904.09730/

## Key facts

- Cited by 163 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Apr 2019.

## Built on by (most cited first, 30 of 163)

- [BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers](https://mlsanity.com/paper/2203.17270/) (2022)
- [Planning-oriented Autonomous Driving](https://mlsanity.com/paper/2212.10156/) (2022)
- [YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors](https://mlsanity.com/paper/2207.02696/) (2022)
- [End-to-end Autonomous Driving: Challenges and Frontiers](https://mlsanity.com/paper/2306.16927/) (2023)
- [Exploring Object-Centric Temporal Modeling for Efficient Multi-View 3D Object Detection](https://mlsanity.com/paper/2303.11926/) (2023)
- [Hydra-MDP: End-to-end Multimodal Planning with Multi-target Hydra-Distillation](https://mlsanity.com/paper/2406.06978/) (2024)
- [RTMDet: An Empirical Study of Designing Real-Time Object Detectors](https://mlsanity.com/paper/2212.07784/) (2022)
- [MapTRv2: An End-to-End Framework for Online Vectorized HD Map Construction](https://mlsanity.com/paper/2308.05736/) (2023)
- [FB-OCC: 3D Occupancy Prediction based on Forward-Backward View Transformation](https://mlsanity.com/paper/2307.01492/) (2023)
- [Sparse4D: Multi-view 3D Object Detection with Sparse Spatial-Temporal Fusion](https://mlsanity.com/paper/2211.10581/) (2022)
- [PolarFormer: Multi-camera 3D Object Detection with Polar Transformer](https://mlsanity.com/paper/2206.15398/) (2022)
- [MPViT: Multi-Path Vision Transformer for Dense Prediction](https://mlsanity.com/paper/2112.11010/) (2021)
- [Language Prompt for Autonomous Driving](https://mlsanity.com/paper/2309.04379/) (2023)
- [FB-BEV: BEV Representation from Forward-Backward View Transformations](https://mlsanity.com/paper/2308.02236/) (2023)
- [Hydra-MDP++: Advancing End-to-End Driving via Expert-Guided Hydra-Distillation](https://mlsanity.com/paper/2503.12820/) (2025)
- [DriveSuprim: Towards Precise Trajectory Selection for End-to-End Planning](https://mlsanity.com/paper/2506.06659/) (2025)
- [Sparse4D v2: Recurrent Temporal Fusion with Sparse Model](https://mlsanity.com/paper/2305.14018/) (2023)
- [PP-YOLOE: An evolved version of YOLO](https://mlsanity.com/paper/2203.16250/) (2022)
- [Far3D: Expanding the Horizon for Surround-view 3D Object Detection](https://mlsanity.com/paper/2308.09616/) (2023)
- [Sparse4D v3: Advancing End-to-End 3D Detection and Tracking](https://mlsanity.com/paper/2311.11722/) (2023)
- [Generalized Trajectory Scoring for End-to-end Multimodal Planning](https://mlsanity.com/paper/2506.06664/) (2025)
- [Standing Between Past and Future: Spatio-Temporal Modeling for Multi-Camera 3D Multi-Object Tracking](https://mlsanity.com/paper/2302.03802/) (2023)
- [Polar Parametrization for Vision-based Surround-View 3D Detection](https://mlsanity.com/paper/2206.10965/) (2022)
- [Efficient Deformable ConvNets: Rethinking Dynamic and Sparse Operator for Vision Applications](https://mlsanity.com/paper/2401.06197/) (2024)
- [Temporal Enhanced Training of Multi-view 3D Object Detector via Historical Object Prediction](https://mlsanity.com/paper/2304.00967/) (2023)
- [Driving on Registers](https://mlsanity.com/paper/2601.05083/) (2026)
- [Stream Query Denoising for Vectorized HD Map Construction](https://mlsanity.com/paper/2401.09112/) (2024)
- [Online Vectorized HD Map Construction using Geometry](https://mlsanity.com/paper/2312.03341/) (2023)
- [DistillBEV: Boosting Multi-Camera 3D Object Detection with Cross-Modal Knowledge Distillation](https://mlsanity.com/paper/2309.15109/) (2023)
- [TopoMLP: A Simple yet Strong Pipeline for Driving Topology Reasoning](https://mlsanity.com/paper/2310.06753/) (2023)

## Abstract (arXiv)

As DenseNet conserves intermediate features with diverse receptive fields by aggregating them with dense connection, it shows good performance on the object detection task. Although feature reuse enables DenseNet to produce strong features with a small number of model parameters and FLOPs, the detector with DenseNet backbone shows rather slow speed and low energy efficiency. We find the linearly increasing input channel by dense connection leads to heavy memory access cost, which causes computation overhead and more energy consumption. To solve the inefficiency of DenseNet, we propose an energy and computation efficient architecture called VoVNet comprised of One-Shot Aggregation (OSA). The OSA not only adopts the strength of DenseNet that represents diversified features with multi receptive fields but also overcomes the inefficiency of dense connection by aggregating all features only once in the last feature maps. To validate the effectiveness of VoVNet as a backbone network, we design both lightweight and large-scale VoVNet and apply them to one-stage and two-stage object detectors. Our VoVNet based detectors outperform DenseNet based ones with 2x faster speed and the energy consumptions are reduced by 1.6x - 4.1x. In addition to DenseNet, VoVNet also outperforms widely used ResNet backbone with faster speed and better energy efficiency. In particular, the small object detection performance has been significantly improved over DenseNet and ResNet.