mlsanityData to 7 Oct 2026

R-TOSS: A Framework for Real-Time Object Detection using Semi-Structured Pruning

arXiv 2303.02191 ↗First posted 3 Mar 2023cs.CV cs.AI cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

Object detectors used in autonomous vehicles can have high memory and computational overheads. In this paper, we introduce a novel semi-structured pruning framework called R-TOSS that overcomes the shortcomings of state-of-the-art model pruning techniques. Experimental results on the JetsonTX2 show that R-TOSS has a compression rate of 4.4x on the YOLOv5 object detector with a 2.15x speedup in inference time and 57.01% decrease in energy usage. R-TOSS also enables 2.89x compression on RetinaNet with a 1.86x speedup in inference time and 56.31% decrease in energy usage. We also demonstrate significant improvements compared to various state-of-the-art pruning techniques.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 24 of its 41 references that are in the map. First posted on arXiv 3 Mar 2023.

Builds on

24 of 41 references.

References · 24

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  2. 2020End-to-End Object Detection with Transformerscited by 7,384
  3. 2015Fast R-CNNcited by 2,930
  4. 2013Rich feature hierarchies for accurate object detection and semantic segmentationcited by 2,160
  5. 2020YOLOv4: Optimal Speed and Accuracy of Object Detectioncited by 1,624
  6. 2016Pruning Filters for Efficient ConvNetscited by 1,129
  7. 2021YOLOX: Exceeding YOLO Series in 2021cited by 1,064
  8. 2022YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectorscited by 978
  9. 2018SNIP: Single-shot Network Pruning based on Connection Sensitivitycited by 802
  10. 2017Learning Efficient Convolutional Networks through Network Slimmingcited by 673
  11. 2019Importance Estimation for Neural Network Pruningcited by 531
  12. 2020Pruning neural networks without any data by iteratively conserving synaptic flowcited by 475
12 more
  1. 2019The State of Sparsity in Deep Neural Networkscited by 471
  2. 2020Picking Winning Tickets Before Training by Preserving Gradient Flowcited by 467
  3. 2018Deep Learning for Generic Object Detection: A Surveycited by 392
  4. 2020Neural Pruning via Growing Regularizationcited by 97
  5. 2021You Only Learn One Representation: Unified Network for Multiple Taskscited by 86
  6. 2020PatDNN: Achieving Real-Time DNN Execution on Mobile Devices with Pattern-based Weight Pruningcited by 75
  7. 2020YOLObile: Real-Time Object Detection on Mobile Devices via Compression-Compilation Co-Designcited by 24
  8. 2019Localization-aware Channel Pruning for Object Detectioncited by 13
  9. 2021SONIC: A Sparse Neural Network Inference Accelerator with Silicon Photonics for Energy-Efficient Deep Learningcited by 10
  10. 2021LATTE: LSTM Self-Attention based Anomaly Detection in Embedded Automotive Platformscited by 9
  11. 2022Roadmap for Cybersecurity in Autonomous Vehiclescited by 5
  12. 2022Robust Perception Architecture Design for Automotive Cyber-Physical Systemscited by 4

Built on by

Cited by year

Citing papers per year: 2024: 2; 2025: 2.

4 papers.

  1. 2024Online Robot Navigation and Manipulation with Distilled Vision-Language Modelscited by 1
  2. 2024Optical Computing for Deep Neural Network Acceleration: Foundations, Recent Developments, and Emerging Directionscited by 0
  3. 2025UPAQ: A Framework for Real-Time and Energy-Efficient 3D Object Detection in Autonomous Vehiclescited by 0
  4. 2025A Novel Compression Framework for YOLOv8: Achieving Real-Time Aerial Object Detection on Edge Devices via Structured Pruning and Channel-Wise Distillationcited by 0