mlsanityData to 7 Oct 2026

Single-Training Collaborative Object Detectors Adaptive to Bandwidth and Computation

arXiv 2105.00591 ↗First posted 3 May 2021cs.CV cs.LGcited by 6

Not on the map. Why?

Abstract (arXiv)

In the past few years, mobile deep-learning deployment progressed by leaps and bounds, but solutions still struggle to accommodate its severe and fluctuating operational restrictions, which include bandwidth, latency, computation, and energy. In this work, we help to bridge that gap, introducing the first configurable solution for object detection that manages the triple communication-computation-accuracy trade-off with a single set of weights. Our solution shows state-of-the-art results on COCO-2017, adding only a minor penalty on the base EfficientDet-D2 architecture. Our design is robust to the choice of base architecture and compressor and should adapt well for future architectures.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 31 of its 44 references that are in the map. First posted on arXiv 3 May 2021.

Builds on

31 of 44 references.

References · 31

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  2. 2019EfficientDet: Scalable and Efficient Object Detectioncited by 1,018
  3. 2016Deep Networks with Stochastic Depthcited by 973
  4. 2015Deep Learning and the Information Bottleneck Principlecited by 793
  5. 2019Once-for-All: Train One Network and Specialize it for Efficient Deploymentcited by 778
  6. 2016End-to-end Optimized Image Compressioncited by 673
  7. 2017BranchyNet: Fast Inference via Early Exiting from Deep Neural Networkscited by 591
  8. 2018Slimmable Neural Networkscited by 301
  9. 2019Universally Slimmable Networks and Improved Training Techniquescited by 219
  10. 2017Emergence of Invariance and Disentanglement in Deep Representationscited by 213
  11. 2020Resolution Adaptive Networks for Efficient Inferencecited by 146
  12. 2016Designing Energy-Efficient Convolutional Neural Networks using Energy-Aware Pruningcited by 133
19 more
  1. 2019Convergence of Edge Computing and Deep Learning: A Comprehensive Surveycited by 120
  2. 2020Communication-Efficient Edge AI: Algorithms and Systemscited by 95
  3. 2019BottleNet++: An End-to-End Approach for Feature Compression in Device-Edge Co-Inference Systemscited by 94
  4. 2018JointDNN: An Efficient Training and Inference Engine for Intelligent Mobile Cloud Computing Servicescited by 79
  5. 2019BottleNet: A Deep Learning Architecture for Intelligent Mobile Cloud Computing Servicescited by 67
  6. 2020Communication-Computation Trade-Off in Resource-Constrained Edge Inferencecited by 60
  7. 2018Deep feature compression for collaborative object detectioncited by 48
  8. 2019MutualNet: Adaptive ConvNet via Mutual Learning from Network Width and Resolutioncited by 36
  9. 2020Neural Compression and Filtering for Edge-assisted Real-time Object Detection in Challenged Networkscited by 28
  10. 2021Collaborative Intelligence: Challenges and Opportunitiescited by 18
  11. 2018Near-Lossless Deep Feature Compression for Collaborative Intelligencecited by 17
  12. 2020Comparison and Benchmarking of AI Models and Frameworks on Mobile Devicescited by 17
  13. 2020Back-and-Forth prediction for deep tensor compressioncited by 16
  14. 2020Bit Allocation for Multi-Task Collaborative Intelligencecited by 13
  15. 2018DeepSIC: Deep Semantic Image Compressioncited by 10
  16. 2019Towards Collaborative Intelligence Friendly Architectures for Deep Learningcited by 7
  17. 2020Split Computing for Complex Object Detectors: Challenges and Preliminary Resultscited by 7
  18. 2019Compressing Representations for Embedded Deep Learningcited by 2
  19. 2016Deep Neural Networks Under Stresscited by 1

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 2; 2024: 2; 2025: 1.

6 papers.

  1. 2022SplitNets: Designing Neural Architectures for Efficient Distributed Computing on Head-Mounted Systemscited by 13
  2. 2023Adaptive Compression-Aware Split Learning and Inference for Enhanced Network Efficiencycited by 8
  3. 2023Slimmable Encoders for Flexible Split DNNs in Bandwidth and Resource Constrained IoT Systemscited by 3
  4. 2024On the Impact of Black-box Deployment Strategies for Edge AI on Latency and Model Performancecited by 3
  5. 2024On the Impact of White-box Deployment Strategies for Edge AI on Latency and Model Performancecited by 1
  6. 2025LimitNet: Progressive, Content-Aware Image Offloading for Extremely Weak Devices & Networkscited by 1