# Anatomizing Deep Learning Inference in Web Browsers

arXiv: https://arxiv.org/abs/2402.05981 · HTML: https://mlsanity.com/paper/2402.05981/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 105 references that are in the map.
- First posted on arXiv 8 Feb 2024.

## Builds on (most cited first, 30 of 33)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [Progressive Growing of GANs for Improved Quality, Stability, and Variation](https://mlsanity.com/paper/1710.10196/) (2017)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [Searching for MobileNetV3](https://mlsanity.com/paper/1905.02244/) (2019)
- [ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks](https://mlsanity.com/paper/1809.00219/) (2018)
- [EfficientDet: Scalable and Efficient Object Detection](https://mlsanity.com/paper/1911.09070/) (2019)
- [CosFace: Large Margin Cosine Loss for Deep Face Recognition](https://mlsanity.com/paper/1801.09414/) (2018)
- [Towards Federated Learning at Scale: System Design](https://mlsanity.com/paper/1902.01046/) (2019)
- [MobileBERT: a Compact Task-Agnostic BERT for Resource-Limited Devices](https://mlsanity.com/paper/2004.02984/) (2020)
- [LaSOT: A High-quality Benchmark for Large-scale Single Object Tracking](https://mlsanity.com/paper/1809.07845/) (2018)
- [Exploring Object Relation in Mean Teacher for Cross-Domain Detection](https://mlsanity.com/paper/1904.11245/) (2019)
- [Flowing ConvNets for Human Pose Estimation in Videos](https://mlsanity.com/paper/1506.02897/) (2015)
- [A Survey on Deep Learning for Software Engineering](https://mlsanity.com/paper/2011.14597/) (2020)
- [Scaling Video Analytics on Constrained Edge Nodes](https://mlsanity.com/paper/1905.13536/) (2019)
- [An Empirical Study towards Characterizing Deep Learning Development and Deployment across Different Frameworks and Platforms](https://mlsanity.com/paper/1909.06727/) (2019)
- [An Empirical Study on Deployment Faults of Deep Learning Based Mobile Applications](https://mlsanity.com/paper/2101.04930/) (2021)
- [LUT-NN: Empower Efficient Neural Network Inference with Centroid Learning and Table Lookup](https://mlsanity.com/paper/2302.03213/) (2023)
- [DeepPerform: An Efficient Approach for Performance Testing of Resource-Constrained Neural Networks](https://mlsanity.com/paper/2210.05370/) (2022)
- [ReQA: An Evaluation for End-to-End Answer Retrieval Models](https://mlsanity.com/paper/1907.04780/) (2019)
- [SqueezeNeRF: Further factorized FastNeRF for memory-efficient inference](https://mlsanity.com/paper/2204.02585/) (2022)
- [Moving Deep Learning into Web Browser: How Far Can We Go?](https://mlsanity.com/paper/1901.09388/) (2019)
- [Understanding Performance Problems in Deep Learning Systems](https://mlsanity.com/paper/2112.01771/) (2021)
- [Benchmarking of DL Libraries and Models on Mobile Devices](https://mlsanity.com/paper/2202.06512/) (2022)
- [Objects do not disappear: Video object detection by single-frame object location anticipation](https://mlsanity.com/paper/2308.04770/) (2023)
- [Interpreting Cloud Computer Vision Pain-Points: A Mining Study of Stack Overflow](https://mlsanity.com/paper/2001.10130/) (2020)

## Built on by (most cited first, 6 of 6)

- [DejAIvu: Identifying and Explaining AI Art on the Web in Real-Time with Saliency Maps](https://mlsanity.com/paper/2502.08821/) (2025)
- [In-Browser Agents for Search Assistance](https://mlsanity.com/paper/2601.09928/) (2026)
- [Decentralized Direct Volume Rendering: A Browser-Native GPU Architecture for MRI Digital Twins in Resource-Constrained Settings](https://mlsanity.com/paper/2605.19737/) (2026)
- [As We May Search](https://mlsanity.com/paper/2606.29652/) (2026)
- [Privacy-Friendly Cohort Determination: Sealed, CSP-Independent In-Browser ML Inference of Professional Segments for Identity-Less Advertising](https://mlsanity.com/paper/2609.36153/) (2026)
- [GPU Goldmines: Tunable WebGPU Kernels for Edge LLM Inference](https://mlsanity.com/paper/2610.17321/) (2026)

## Abstract (arXiv)

Web applications have increasingly adopted Deep Learning (DL) through in-browser inference, wherein DL inference performs directly within Web browsers. The actual performance of in-browser inference and its impacts on the quality of experience (QoE) remain unexplored, and urgently require new QoE measurements beyond traditional ones, e.g., mainly focusing on page load time. To bridge this gap, we make the first comprehensive performance measurement of in-browser inference to date. Our approach proposes new metrics to measure in-browser inference: responsiveness, smoothness, and inference accuracy. Our extensive analysis involves 9 representative DL models across Web browsers of 50 popular PC devices and 20 mobile devices. The results reveal that in-browser inference exhibits a substantial latency gap, averaging 16.9 times slower on CPU and 4.9 times slower on GPU compared to native inference on PC devices. The gap on mobile CPU and mobile GPU is 15.8 times and 7.8 times, respectively. Furthermore, we identify contributing factors to such latency gap, including underutilized hardware instruction sets, inherent overhead in the runtime environment, resource contention within the browser, and inefficiencies in software libraries and GPU abstractions. Additionally, in-browser inference imposes significant memory demands, at times exceeding 334.6 times the size of the DL models themselves, partly attributable to suboptimal memory management. We also observe that in-browser inference leads to a significant 67.2% increase in the time it takes for GUI components to render within Web browsers, significantly affecting the overall user QoE of Web applications reliant on this technology