mlsanityData to 14 Oct 2026

An Analysis of Deep Neural Network Models for Practical Applications

arXiv 1605.07678 ↗First posted 24 May 2016cs.CVcited by 116

Not on the map. Why?

Abstract (arXiv)

Since the emergence of Deep Neural Networks (DNNs) as a prominent technique in the field of computer vision, the ImageNet classification challenge has played a major role in advancing the state-of-the-art. While accuracy figures have steadily increased, the resource utilisation of winning models has not been properly taken into account. In this work, we present a comprehensive analysis of important metrics in practical applications: accuracy, memory footprint, parameters, operations count, inference time and power consumption. Key findings are: (1) power consumption is independent of batch size and architecture; (2) accuracy and inference time are in a hyperbolic relationship; (3) energy constraint is an upper bound on the maximum achievable accuracy and model complexity; (4) the number of operations is a reliable estimate of the inference time. We believe our analysis provides a compelling set of information that helps design and engineer efficient DNNs.

Key facts. Cited by 116 papers in the map (data through 14 Oct 2026). First posted on arXiv 24 May 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 32; 2022: 20; 2023: 26; 2024: 21; 2025: 7; 2026: 10.

116 papers.

Sort:

By area:

  1. 2021Fit without fear: remarkable mathematical phenomena of deep learning through the prism of interpolationcited by 132
  2. 2021Compute and Energy Consumption Trends in Deep Learning Inferencecited by 61
  3. 2023When Does Confidence-Based Cascade Deferral Suffice?cited by 60
  4. 2022SparCL: Sparse Continual Learning on the Edgecited by 55
  5. 2024Tiny Machine Learning: Progress and Futurescited by 40
  6. 2021Early-Bird GCNs: Graph-Network Co-Optimization Towards More Efficient GCN Training and Inference via Drawing Early-Bird Lottery Ticketscited by 27
  7. 2022Spiking Graph Convolutional Networkscited by 27
  8. 2023Model scale versus domain knowledge in statistical forecasting of chaotic systemscited by 27
  9. 2021A survey on Variational Autoencoders from a GreenAI perspectivecited by 22
  10. 2022Great Power, Great Responsibility: Recommendations for Reducing Energy for Training Language Modelscited by 21
  11. 2022SplitGP: Achieving Both Generalization and Personalization in Federated Learningcited by 20
  12. 2021PyGlove: Symbolic Programming for Automated Machine Learningcited by 19
38 more
  1. 2023Zero-Knowledge Proof-based Verifiable Decentralized Machine Learning in Communication Network: A Comprehensive Surveycited by 18
  2. 2024On the Limitations of Compute Thresholds as a Governance Strategycited by 18
  3. 2021AI Accelerator Survey and Trendscited by 17
  4. 2021Silicon Photonic Architecture for Training Deep Neural Networks with Direct Feedback Alignmentcited by 17
  5. 2023Joint Edge-Model Sparse Learning is Provably Efficient for Graph Neural Networkscited by 16
  6. 2024SoK: Dataset Copyright Auditing in Machine Learning Systemscited by 15
  7. 2022On the in vivo recognition of kidney stones using machine learningcited by 14
  8. 2022DarKnight: An Accelerated Framework for Privacy and Integrity Preserving Deep Learning Using Trusted Hardwarecited by 14
  9. 2025Device-Cloud Collaborative LLM Inference with Multi-Modal, Multi-Task, Multi-Turn Conversationscited by 14
  10. 2021Privacy and Trust Redefined in Federated Machine Learningcited by 13
  11. 2021GCoD: Graph Convolutional Network Acceleration via Dedicated Algorithm and Accelerator Co-Designcited by 13
  12. 2023Eventful Transformers: Leveraging Temporal Redundancy in Vision Transformerscited by 13
  13. 2022Learning from Randomly Initialized Neural Network Featurescited by 12
  14. 2022A Multi-dimensional Evaluation of Tokenizer-free Multilingual Pretrained Modelscited by 12
  15. 2021VAC-CNN: A Visual Analytics System for Comparative Studies of Deep Convolutional Neural Networkscited by 11
  16. 2021Mobile Augmented Reality: User Interfaces, Frameworks, and Intelligencecited by 10
  17. 2021Design Smells in Deep Learning Programs: An Empirical Studycited by 10
  18. 2021Automatic Fault Detection for Deep Learning Programs Using Graph Transformationscited by 9
  19. 2023Which Transformer to Favor: A Comparative Analysis of Efficiency in Vision Transformerscited by 9
  20. 2023Exploring the Privacy-Energy Consumption Tradeoff for Split Federated Learningcited by 9
  21. 2021Classification of Urban Morphology with Deep Learning: Application on Urban Vitalitycited by 8
  22. 2021Bangla Natural Language Processing: A Comprehensive Analysis of Classical, Machine Learning, and Deep Learning Based Methodscited by 8
  23. 2023Quantum-limited stochastic optical neural networks operating at a few quanta per activationcited by 8
  24. 2021Dubhe: Towards Data Unbiasedness with Homomorphic Encryption in Federated Learning Client Selectioncited by 7
  25. 2022Energy-efficient Deployment of Deep Learning Applications on Cortex-M based Microcontrollers using Deep Compressioncited by 7
  26. 2023Sketched Ridgeless Linear Regression: The Role of Downsamplingcited by 7
  27. 2024Learn to Code Sustainably: An Empirical Study on LLM-based Green Code Generationcited by 7
  28. 2024Nexus: Specialization meets Adaptability for Efficiently Training Mixture of Expertscited by 7
  29. 2024Double-Exponential Increases in Inference Energy: The Cost of the Race for Accuracycited by 6
  30. 2021CADA: Multi-scale Collaborative Adversarial Domain Adaptation for Unsupervised Optic Disc and Cup Segmentationcited by 5
  31. 2021Approximation of functions with one-bit neural networkscited by 5
  32. 2024How green is continual learning, really? Analyzing the energy consumption in continual training of vision foundation modelscited by 5
  33. 2022Topological Structure Learning for Weakly-Supervised Out-of-Distribution Detectioncited by 4
  34. 2022A Fair Loss Function for Network Pruningcited by 4
  35. 2023Tackling Data Bias in Painting Classification with Style Transfercited by 3
  36. 2023Pneumonia Detection in Chest X-Ray Images : Handling Class Imbalancecited by 3
  37. 2023rm A2Q: Aggregation-Aware Quantization for Graph Neural Networkscited by 3
  38. 2023Cheaply Evaluating Inference Efficiency Metrics for Autoregressive Transformer APIscited by 3

50 most cited of 116 All 116 (JSON)