# DeepCache: Principled Cache for Mobile Deep Vision

arXiv: https://arxiv.org/abs/1712.01670 · HTML: https://mlsanity.com/paper/1712.01670/

## Key facts

- Cited by 57 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Dec 2017.

## Built on by (most cited first, 30 of 57)

- [Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model](https://mlsanity.com/paper/2411.19108/) (2024)
- [EdgeMoE: Empowering Sparse Large Language Models on Mobile Devices](https://mlsanity.com/paper/2308.14352/) (2023)
- [Fast On-device LLM Inference with NPUs](https://mlsanity.com/paper/2407.05858/) (2024)
- [LLMCad: Fast and Scalable On-device Large Language Model Inference](https://mlsanity.com/paper/2309.04255/) (2023)
- [Less is Enough: Training-Free Video Diffusion Acceleration via Runtime-Adaptive Caching](https://mlsanity.com/paper/2507.02860/) (2025)
- [FlashVSR: Towards Real-Time Diffusion-Based Streaming Video Super-Resolution](https://mlsanity.com/paper/2510.12747/) (2025)
- [DiCache: Let Diffusion Model Determine Its Own Cache](https://mlsanity.com/paper/2508.17356/) (2025)
- [MagCache: Fast Video Generation with Magnitude-Aware Cache](https://mlsanity.com/paper/2506.09045/) (2025)
- [Achieving on-Mobile Real-Time Super-Resolution with Neural Architecture and Pruning Search](https://mlsanity.com/paper/2108.08910/) (2021)
- [Region-Adaptive Sampling for Diffusion Transformers](https://mlsanity.com/paper/2502.10389/) (2025)
- [FEDZIP: A Compression Framework for Communication-Efficient Federated Learning](https://mlsanity.com/paper/2102.01593/) (2021)
- [Mobile Foundation Model as Firmware](https://mlsanity.com/paper/2308.14363/) (2023)
- [SocialMind: LLM-based Proactive AR Social Assistive System with Human-like Perception for In-situ Live Interactions](https://mlsanity.com/paper/2412.04036/) (2024)
- [Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers](https://mlsanity.com/paper/2412.16822/) (2024)
- [EdgeFM: Leveraging Foundation Model for Open-set Learning on the Edge](https://mlsanity.com/paper/2311.10986/) (2023)
- [An Empirical Study on Deployment Faults of Deep Learning Based Mobile Applications](https://mlsanity.com/paper/2101.04930/) (2021)
- [Compiler-Aware Neural Architecture Search for On-Mobile Real-time Super-Resolution](https://mlsanity.com/paper/2207.12577/) (2022)
- [On-device Training: A First Overview on Existing Systems](https://mlsanity.com/paper/2212.00824/) (2022)
- [AdaptiveNet: Post-deployment Neural Architecture Adaptation for Diverse Edge Environments](https://mlsanity.com/paper/2303.07129/) (2023)
- [SCALM: Towards Semantic Caching for Automated Chat Services with Large Language Models](https://mlsanity.com/paper/2406.00025/) (2024)
- [Towards Artificial General Intelligence (AGI) in the Internet of Things (IoT): Opportunities and Challenges](https://mlsanity.com/paper/2309.07438/) (2023)
- [Benchmarking of DL Libraries and Models on Mobile Devices](https://mlsanity.com/paper/2202.06512/) (2022)
- [SmartMem: Layout Transformation Elimination and Adaptation for Efficient DNN Execution on Mobile](https://mlsanity.com/paper/2404.13528/) (2024)
- [Boggart: Towards General-Purpose Acceleration of Retrospective Video Analytics](https://mlsanity.com/paper/2106.15315/) (2021)
- [GRIM: A General, Real-Time Deep Learning Inference Framework for Mobile Devices based on Fine-Grained Structured Weight Sparsity](https://mlsanity.com/paper/2108.11033/) (2021)
- [Continual 3D Convolutional Neural Networks for Real-time Processing of Videos](https://mlsanity.com/paper/2106.00050/) (2021)
- [Automatic Mapping of the Best-Suited DNN Pruning Schemes for Real-Time Mobile Acceleration](https://mlsanity.com/paper/2111.11581/) (2021)
- [AccMPEG: Optimizing Video Encoding for Video Analytics](https://mlsanity.com/paper/2204.12534/) (2022)
- [Edge Video Analytics: A Survey on Applications, Systems and Enabling Techniques](https://mlsanity.com/paper/2211.15751/) (2022)
- [MadEye: Boosting Live Video Analytics Accuracy with Adaptive Camera Configurations](https://mlsanity.com/paper/2304.02101/) (2023)

## 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.