Performance Bottlenecks and Solutions in Deep Learning for Image Recognition
Research Article
Open Access
CC BY

Performance Bottlenecks and Solutions in Deep Learning for Image Recognition

Zikai Chen 1*
1 Department of Physics, King’s College London, London WC2R 2LS, United Kingdom
*Corresponding author: weudawn@163.com
Published on 28 October 2025
Journal Cover
ACE Vol.202
ISSN (Print): 2755-273X
ISSN (Online): 2755-2721
ISBN (Print): 978-1-80590-497-7
ISBN (Online): 978-1-80590-498-4
Download Cover

Abstract

Deep learning has advanced image recognition, achieving strong results in medical imaging, autonomous driving, and security. Yet significant bottlenecks still limit deployment. This paper reviews three main challenges: weak robustness, high computational demands, and reliance on large labeled datasets. Recent studies identify the causes of these issues, including growing model complexity, distribution shifts between training and real data, and lack of security-aware design. To address these problems, various strategies have been developed in the past five years. For robustness, adversarial training, data augmentation, and domain adaptation have been widely applied. To enhance the efficiency of deep learning models, techniques including network pruning, parameter quantization, and lightweight architectures (e.g., MobileNet and EfficientNet) are widely adopted—often augmented by knowledge distillation and hardware-aware neural architecture search (NAS). To mitigate reliance on large-scale labeled datasets, approaches such as transfer learning, self-supervised learning frameworks (e.g., SimCLR and BYOL), and multimodal models (e.g., CLIP) have demonstrated promising performance. While progress is evident, trade-offs remain. Future work should focus on combining these strategies to achieve models that are simultaneously accurate, efficient, and robust for real-world applications.

Keywords:

deep learning, image recognition, robustness, efficiency, transfer learning

View PDF
Chen,Z. (2025). Performance Bottlenecks and Solutions in Deep Learning for Image Recognition. Applied and Computational Engineering,202,1-7.

References

[1]. Javed H, El-Sappagh S, Abuhmed T. (2024) Robustness in deep learning models for medical diagnostics: security and adversarial challenges towards robust AI applications. Artif Intell Rev

[2]. Balendran A, Beji C, Bouvier F, Khalifa O, Evgeniou T, Ravaud P, et al. (2025) A scoping review of robustness concepts for machine learning in healthcare. npj Digit Med, 8: 38

[3]. Dantas PV, da Silva Jr W, Carvalho LC, Carvalho CB. (2024) A comprehensive review of model compression techniques in machine learning. Appl Intell, 54: 11804–11844

[4]. Liu D, Zhu Y, Liu Z, Liu Y, Han C, Tian J, et al. (2025) A survey of model compression techniques: past, present, and future. Front Robot AI

[5]. Liu J, Zhang K, Wang H, Chen L. (2023) A comprehensive survey of robust deep learning in computer vision. Comput Vis Image Underst, 229: 1036576.

[6]. Wang J, Ai J, Lu M, Su H, Yu D, Zhang Y, et al. (2024) A survey of neural network robustness assessment in image recognition. arXiv [Internet]. 2024 Apr 12 [cited 2025 Aug 17]. Available from: https: //arxiv.org/abs/2404.08285

[7]. Paula E, Soni J, Upadhyay H, Lagos L. (2025) Comparative analysis of model compression techniques for achieving carbon efficient AI. Sci Rep, 15(1): 23461. DOI: 10.1038/s41598-025-07821-w

[8]. Khan Z, Ali S, Rehman S, Zhang T, Hussain F. (2025) Deep learning model compression and hardware acceleration for efficient deployment. Sensors, 25(3): 970

[9]. Trigka M. (2025) A comprehensive survey of deep learning approaches in image analysis. Sensors, 25(2): 531. DOI: 10.3390/s25020531

[10]. Howard AG, Zhu M, Chen B, Kalenichenko D, Wang W, Weyand T, Andreetto M, Adam H. (2017) MobileNets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv: 1704.04861 [Internet]. Available from: https: //arxiv.org/abs/1704.04861

References

[1]. Javed H, El-Sappagh S, Abuhmed T. (2024) Robustness in deep learning models for medical diagnostics: security and adversarial challenges towards robust AI applications. Artif Intell Rev

[2]. Balendran A, Beji C, Bouvier F, Khalifa O, Evgeniou T, Ravaud P, et al. (2025) A scoping review of robustness concepts for machine learning in healthcare. npj Digit Med, 8: 38

[3]. Dantas PV, da Silva Jr W, Carvalho LC, Carvalho CB. (2024) A comprehensive review of model compression techniques in machine learning. Appl Intell, 54: 11804–11844

[4]. Liu D, Zhu Y, Liu Z, Liu Y, Han C, Tian J, et al. (2025) A survey of model compression techniques: past, present, and future. Front Robot AI

[5]. Liu J, Zhang K, Wang H, Chen L. (2023) A comprehensive survey of robust deep learning in computer vision. Comput Vis Image Underst, 229: 1036576.

[6]. Wang J, Ai J, Lu M, Su H, Yu D, Zhang Y, et al. (2024) A survey of neural network robustness assessment in image recognition. arXiv [Internet]. 2024 Apr 12 [cited 2025 Aug 17]. Available from: https: //arxiv.org/abs/2404.08285

[7]. Paula E, Soni J, Upadhyay H, Lagos L. (2025) Comparative analysis of model compression techniques for achieving carbon efficient AI. Sci Rep, 15(1): 23461. DOI: 10.1038/s41598-025-07821-w

[8]. Khan Z, Ali S, Rehman S, Zhang T, Hussain F. (2025) Deep learning model compression and hardware acceleration for efficient deployment. Sensors, 25(3): 970

[9]. Trigka M. (2025) A comprehensive survey of deep learning approaches in image analysis. Sensors, 25(2): 531. DOI: 10.3390/s25020531

[10]. Howard AG, Zhu M, Chen B, Kalenichenko D, Wang W, Weyand T, Andreetto M, Adam H. (2017) MobileNets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv: 1704.04861 [Internet]. Available from: https: //arxiv.org/abs/1704.04861

Cite this article

Chen,Z. (2025). Performance Bottlenecks and Solutions in Deep Learning for Image Recognition. Applied and Computational Engineering,202,1-7.

Data availability

The datasets used and/or analyzed during the current study will be available from the authors upon reasonable request.

About volume

Volume title: Proceedings of CONF-MLA 2025 Symposium: Intelligent Systems and Automation: AI Models, IoT, and Robotic Algorithms

ISBN: 978-1-80590-497-7(Print) / 978-1-80590-498-4(Online)
Editor: Hisham AbouGrad
Conference website: https://www.confmla.org/london.html
Conference date: 12 November 2025
Series: Applied and Computational Engineering
Volume number: Vol.202
ISSN: 2755-2721(Print) / 2755-273X(Online)

© 2024 by the author(s). Licensee EWA Publishing, Oxford, UK. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license. Authors who publish this series agree to the following terms:

1. Authors retain copyright and grant the series right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this series.

2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the series's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this series.

3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See Open access policy for details).

For authors
For editors
For reviewers

Cookies are used by this site.
Copyright © 2024 EWA Publishing, its licensors, and contributors. All rights reserved, including text and data mining, AI training, and similar technologies.