mlsanityData to 7 Oct 2026

DeepCache: Principled Cache for Mobile Deep Vision

arXiv 1712.01670 ↗First posted 1 Dec 2017cs.CVcited by 57

Not on the map. Why?

Abstract (arXiv)

We present DeepCache, a principled cache design for deep learning inference in continuous mobile vision. DeepCache benefits model execution efficiency by exploiting temporal locality in input video streams. It addresses a key challenge raised by mobile vision: the cache must operate under video scene variation, while trading off among cacheability, overhead, and loss in model accuracy. At the input of a model, DeepCache discovers video temporal locality by exploiting the video's internal structure, for which it borrows proven heuristics from video compression; into the model, DeepCache propagates regions of reusable results by exploiting the model's internal structure. Notably, DeepCache eschews applying video heuristics to model internals which are not pixels but high-dimensional, difficult-to-interpret data. Our implementation of DeepCache works with unmodified deep learning models, requires zero developer's manual effort, and is therefore immediately deployable on off-the-shelf mobile devices. Our experiments show that DeepCache saves inference execution time by 18% on average and up to 47%. DeepCache reduces system energy consumption by 20% on average.

Key facts. Cited by 57 papers in the map (data through 7 Oct 2026). First posted on arXiv 1 Dec 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 12; 2022: 8; 2023: 10; 2024: 10; 2025: 11; 2026: 6.

57 papers.

Sort:

By area:

  1. 2024Timestep Embedding Tells: It's Time to Cache for Video Diffusion Modelcited by 245
  2. 2023EdgeMoE: Empowering Sparse Large Language Models on Mobile Devicescited by 65
  3. 2024Fast On-device LLM Inference with NPUscited by 58
  4. 2023LLMCad: Fast and Scalable On-device Large Language Model Inferencecited by 45
  5. 2025FlashVSR: Towards Real-Time Diffusion-Based Streaming Video Super-Resolutioncited by 40
  6. 2025Less is Enough: Training-Free Video Diffusion Acceleration via Runtime-Adaptive Cachingcited by 39
  7. 2025MagCache: Fast Video Generation with Magnitude-Aware Cachecited by 36
  8. 2021Achieving on-Mobile Real-Time Super-Resolution with Neural Architecture and Pruning Searchcited by 34
  9. 2025DiCache: Let Diffusion Model Determine Its Own Cachecited by 34
  10. 2025Region-Adaptive Sampling for Diffusion Transformerscited by 31
  11. 2021FEDZIP: A Compression Framework for Communication-Efficient Federated Learningcited by 27
  12. 2023Mobile Foundation Model as Firmwarecited by 25
38 more
  1. 2024SocialMind: LLM-based Proactive AR Social Assistive System with Human-like Perception for In-situ Live Interactionscited by 25
  2. 2023EdgeFM: Leveraging Foundation Model for Open-set Learning on the Edgecited by 21
  3. 2024Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformerscited by 21
  4. 2021An Empirical Study on Deployment Faults of Deep Learning Based Mobile Applicationscited by 20
  5. 2022Compiler-Aware Neural Architecture Search for On-Mobile Real-time Super-Resolutioncited by 20
  6. 2023AdaptiveNet: Post-deployment Neural Architecture Adaptation for Diverse Edge Environmentscited by 19
  7. 2022On-device Training: A First Overview on Existing Systemscited by 18
  8. 2024SCALM: Towards Semantic Caching for Automated Chat Services with Large Language Modelscited by 16
  9. 2023Towards Artificial General Intelligence (AGI) in the Internet of Things (IoT): Opportunities and Challengescited by 14
  10. 2022Benchmarking of DL Libraries and Models on Mobile Devicescited by 12
  11. 2024SmartMem: Layout Transformation Elimination and Adaptation for Efficient DNN Execution on Mobilecited by 12
  12. 2021Boggart: Towards General-Purpose Acceleration of Retrospective Video Analyticscited by 10
  13. 2021GRIM: A General, Real-Time Deep Learning Inference Framework for Mobile Devices based on Fine-Grained Structured Weight Sparsitycited by 10
  14. 2021Continual 3D Convolutional Neural Networks for Real-time Processing of Videoscited by 9
  15. 2021Automatic Mapping of the Best-Suited DNN Pruning Schemes for Real-Time Mobile Accelerationcited by 7
  16. 2022Edge Video Analytics: A Survey on Applications, Systems and Enabling Techniquescited by 7
  17. 2023MadEye: Boosting Live Video Analytics Accuracy with Adaptive Camera Configurationscited by 7
  18. 2022AccMPEG: Optimizing Video Encoding for Video Analyticscited by 6
  19. 2022Boosting DNN Cold Inference on Edge Devicescited by 6
  20. 2021Boosting Mobile CNN Inference through Semantic Memorycited by 5
  21. 2024MaskVD: Region Masking for Efficient Video Object Detectioncited by 5
  22. 2021DeepScale: Online Frame Size Adaptation for Multi-object Tracking on Smart Cameras and Edge Serverscited by 4
  23. 2023A Comprehensive Review and a Taxonomy of Edge Machine Learning: Requirements, Paradigms, and Techniquescited by 4
  24. 2024SoD2: Statically Optimizing Dynamic Deep Neural Networkcited by 4
  25. 2024DIR-BHRNet: A Lightweight Network for Real-time Vision-based Multi-person Pose Estimation on Smartphonescited by 4
  26. 2025FlashEdit: Decoupling Speed, Structure, and Semantics for Precise Image Editingcited by 4
  27. 2026Beyond Few-Step Inference: Accelerating Video Diffusion Transformer Model Serving with Inter-Request Caching Reusecited by 3
  28. 2021Accelerating Deep Learning Classification with Error-controlled Approximate-key Cachingcited by 2
  29. 2025Communication-Efficient Diffusion Denoising Parallelization via Reuse-then-Predict Mechanismcited by 2
  30. 2022AttTrack: Online Deep Attention Transfer for Multi-object Trackingcited by 1
  31. 2023Learning Online Policies for Person Tracking in Multi-View Environmentscited by 1
  32. 2026FlashMem: Supporting Modern DNN Workloads on Mobile with GPU Memory Hierarchy Optimizationscited by 1
  33. 2021C3DRec: Cloud-Client Cooperative Deep Learning for Temporal Recommendation in the Post-GDPR Eracited by 0
  34. 2021CANS: Communication Limited Camera Network Self-Configuration for Intelligent Industrial Surveillancecited by 0
  35. 2022InFi: End-to-End Learning to Filter Input for Resource-Efficiency in Mobile-Centric Inferencecited by 0
  36. 2023Adaptive Scheduling for Edge-Assisted DNN Servingcited by 0
  37. 2024Mondrian: On-Device High-Performance Video Analytics with Compressive Packed Inferencecited by 0
  38. 2025Q&C: When Quantization Meets Cache in Efficient Image Generationcited by 0

50 most cited of 57 All 57 (JSON)