CoChat
Sign Up
Cited by 932Advanced Neural Network ApplicationsAdvanced Image and Video Retrieval TechniquesDomain Adaptation and Few-Shot Learning

CNN Variants for Computer Vision: History, Architecture, Application, Challenges and Future Scope

Open access
Bhatt, Dulari, Patel, Chirag, Talsania, Hardik, Patel, Jigar, Vaghela, Rasmika, Pandya, Sharnil, Modi, Kirit, Ghayvat, Hemant·2021·Electronics
DOI 10.3390/electronics10202470
Open this paper in CoChat — free accountOpen PDF

Abstract

Computer vision is becoming an increasingly trendy word in the area of image processing. With the emergence of computer vision applications, there is a significant demand to recognize objects automatically. Deep CNN (convolution neural network) has benefited the computer vision community by producing excellent results in video processing, object recognition, picture classification and segmentation, natural language processing, speech recognition, and many other fields. Furthermore, the introduction of large amounts of data and readily available hardware has opened new avenues for CNN study. Several inspirational concepts for the progress of CNN have been investigated, including alternative activation functions, regularization, parameter optimization, and architectural advances. Furthermore, achieving innovations in architecture results in a tremendous enhancement in the capacity of the deep CNN. Significant emphasis has been given to leveraging channel and spatial information, with a depth of architecture and information processing via multi-path. This survey paper focuses mainly on the primary taxonomy and newly released deep CNN architectures, and it divides numerous recent developments in CNN architectures into eight groups. Spatial exploitation, multi-path, depth, breadth, dimension, channel boosting, feature-map exploitation, and attention-based CNN are the eight categories. The main contribution of this manuscript is in comparing various architectural evolutions in CNN by its architectural change, strengths, and weaknesses. Besides, it also includes an explanation of the CNN’s components, the strengths and weaknesses of various CNN variants, research gap or open challenges, CNN applications, and the future research direction.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.3390/electronics10202470

Cites

56 of 56 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • The CNN has found applications in NLP, such as language modeling and analysis, despite RNNs being deemed more appropriate for these purposes.

    “The CNN has found applications in NLP, such as language modeling and analysis, despite RNNs being deemed more appropriate for these purposes (Bhatt et al. 2021).”

    From Large language models (LLMs): survey, technical frameworks, and future challenges (2024) · cites this paper as Bhatt et al. 2021

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

Flagged first, then by citations

1 of the 57 references couldn’t be matched to a known paper.

Research works printed but not linked: 17

  1. Balázs, C.C. Approximation with Artificial Neural Networks. Master's Thesis, Eötvös Loránd University, Budapest, Hungary, 2001.
  2. Ioffe, S. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. arXiv 2015, arXiv:1502.03167. · arXiv
  3. Hanin, B. Approximating Continuous Functions by ReLU Nets of Minimal width. arXiv 2017, arXiv:171011278.
  4. Nguyen, Q. Neural Networks Should Be Wide Enough to Learn Disconnected Decision Regions. arXiv 2018, arXiv:180300094.
  5. He, K. Mask R-CNN. arXiv 2018, arXiv:1703.06870. · arXiv
  6. Lin, C. GRCNN: Graph Recognition Convolutional Neural Network for Synthesizing Programs from Flow Charts. arXiv 2020, arXiv:2011.05980. · arXiv
  7. Ma, D. MFRNet: A New CNN Architecture for Post-Processing and In-loop Filtering. arXiv 2020, arXiv:2007.07099v2. · arXiv
  8. Alexey, B. YOLOv4: Optimal Speed and Accuracy of Object Detection. arXiv 2020, arXiv:2004.10934v1. · arXiv
  9. Aex, B. Net2Vis-A Visual Grammar for Automatically Generating Publication-Tailored CNN Architecture Visualizations. arXiv 2021, arXiv:1902.04394v6. · arXiv
  10. Zou, C.; Zheng, Y.; Su, Q.; Fu, H. Chiew-Lan Tai Sketch-R2CNN: An Attentive Network for Vector Sketch Recognition. arXiv 2018, arXiv:1811.08170v1. · arXiv
  11. Zheng, G. YOLOX: Exceeding YOLO Series in 2021. arXiv 2021, arXiv:2107.08430v2. · arXiv
  12. Defferrard, M. Convolutional neural networks on graphs with fast localized spectral filtering. Adv. Neural Inf. Process. Syst. 2016, 3844-3852.
  13. Kipf, T.N. Semi-supervised classification with graph convolutional networks. arXiv 2016, arXiv:1609.02907. · arXiv
  14. Chen, J. Fastgcn: Fast learning with graph convolutional networks via importance sampling. arXiv 2018, arXiv:1801.10247. · arXiv
  15. Liao, R. Lanczosnet: Multiscale deep graph convolutional networks. arXiv 2019, arXiv:1901.01484. · arXiv
  16. Velickovic, P. Graph attention networks. arXiv 2017, arXiv:1710.10903. · arXiv
  17. De Vries, H. Deep learning vector quantization. In Proceedings of the European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, Bruges, Belgium, 27-29 April 2016.

Cited by

Sorted by citations

Related

Authors
Bhatt, D., Patel, C., Talsania, H., Patel, J., Vaghela, R., Pandya, S., Modi, K., & Ghayvat, H.
Affiliations
  • Parul University (IN)
  • Computer Science & Engineering, DEPSTAR, Changa, Gujarat 388421, India
  • Symbiosis International University (IN)
  • Sankalchand Patel University (IN)
  • Linnaeus University (SE)
Corresponding author
Patel, Chirag
ORCID
Venue
Electronics
Publisher
MDPI AG
Published
2021-10-11
Volume
10
Issue
20
Pages
2470
ISSN
2079-9292 (ISSN-L)
DOI
10.3390/electronics10202470
OpenAlex
W3206824631
Cited by
890
References
57
Citations by year
2026: 100 · 2025: 266 · 2024: 270 · 2023: 189 · 2022: 63 · 2021: 2
FWCI
47.11
Type
journal article
Language
en
Open access
Licence
Locations
  • Electronics (publishedVersion, cc-by)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Topics
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Image and Video Retrieval Techniques
  • Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
Keywords
convolutional neural networks, convolutional neural network architecture, object recognition, image classification, image segmentation, attention-based CNN, channel attention, multipath networks, depthwise convolution, activation functions, regularization

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review