Papers
Topics
Authors
Recent
Search
2000 character limit reached

An evaluation of pre-trained models for feature extraction in image classification

Published 3 Oct 2023 in cs.CV and cs.AI | (2310.02037v1)

Abstract: In recent years, we have witnessed a considerable increase in performance in image classification tasks. This performance improvement is mainly due to the adoption of deep learning techniques. Generally, deep learning techniques demand a large set of annotated data, making it a challenge when applying it to small datasets. In this scenario, transfer learning strategies have become a promising alternative to overcome these issues. This work aims to compare the performance of different pre-trained neural networks for feature extraction in image classification tasks. We evaluated 16 different pre-trained models in four image datasets. Our results demonstrate that the best general performance along the datasets was achieved by CLIP-ViT-B and ViT-H-14, where the CLIP-ResNet50 model had similar performance but with less variability. Therefore, our study provides evidence supporting the choice of models for feature extraction in image classification tasks.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (43)
  1. J.W. Pferd. The challenges of integrating structured and unstructured data. In 14th Petroleum Network Education Conference. s.n, S.l., 2010.
  2. Semantic annotation of image collections. In Knowledge capture, volume 2, 2003.
  3. General multi-label image classification with transformers. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 16478–16488, June 2021.
  4. Imagenet: A large-scale hierarchical image database. In 2009 IEEE conference on computer vision and pattern recognition, pages 248–255. Ieee, 2009.
  5. Utilizing cnns and transfer learning of pre-trained models for age range classification from unconstrained face images. Image and Vision Computing, 88:41–51, 2019.
  6. A comparison of pre-trained language models for multi-class text classification in the financial domain. In Companion Proceedings of the Web Conference 2021, pages 260–268, 2021.
  7. Convolutional neural networks for histopathology image classification: Training vs. using pre-trained networks. In 2017 Seventh International Conference on Image Processing Theory, Tools and Applications (IPTA), pages 1–6. IEEE, 2017.
  8. Comparison of deep transfer learning strategies for digital pathology. In Proceedings of the IEEE conference on computer vision and pattern recognition workshops, pages 2262–2271, 2018.
  9. Multiscale context features for geological image classification. In Joaquim Filipe, Michal Smialek, Alexander Brodsky, and Slimane Hammoudi, editors, Proceedings of the 25th International Conference on Enterprise Information Systems, ICEIS 2023, Volume 1, Prague, Czech Republic, April 24-26, 2023, pages 407–418. SCITEPRESS, 2023.
  10. A knowledge organization system for image classification and retrieval in petroleum exploration domain. In ONTOBRAS, 2019.
  11. Multiscale patch-based feature graphs for image classification. Expert Systems with Applications, 235:121116, 2024.
  12. 3d object representations for fine-grained categorization. In 4th International IEEE Workshop on 3D Representation and Recognition (3dRR-13), Sydney, Australia, 2013.
  13. Learning multiple layers of features from tiny images. 2009.
  14. An analysis of single-layer networks in unsupervised feature learning. In Proceedings of the fourteenth international conference on artificial intelligence and statistics, pages 215–223. JMLR Workshop and Conference Proceedings, 2011.
  15. Laith Alzubaidi et al. Review of deep learning: Concepts, cnn architectures, challenges, applications, future directions. Journal of big Data, 8(1):1–74, 2021.
  16. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929, 2020.
  17. Hiren Maniar et al. Machine-learning methods in geoscience. In 2018 SEG International Exposition and Annual Meeting. OnePetro, 2018.
  18. Anuj Karpatne et al. Machine learning for the geosciences: Challenges and opportunities. IEEE Transactions on Knowledge and Data Engineering, 31(8):1544–1554, 2018.
  19. Hassan Ismail Fawaz et al. Transfer learning for time series classification. In 2018 IEEE international conference on big data (Big Data), pages 1367–1376. IEEE p, 2018.
  20. Deep learning and transfer learning features for plankton classification. Ecological informatics, 51:33–43, 2019.
  21. Transfer learning based performance comparison of the pre-trained deep neural networks. International Journal of Advanced Computer Science and Applications, 13:1, 2022.
  22. Uwe. a transfer learning evaluation of deep neural networks for image classification. Machine Learning and Knowledge Extraction, 4(1):22–41, 2022.
  23. Rafael Pires De Lima et al. Deep convolutional neural networks as a geological image classification tool. The Sedimentary Record, 17(2):4–9, 2019.
  24. Huiming Sun et al. Convolutional neural networks based remote sensing scene classification under clear and cloudy environments. In Proceedings of the IEEE/CVF International Conference on Computer Vision p, pages 713–720, 2021.
  25. Daniel Chevitarese et al. Transfer learning applied to seismic images classification. AAPG Annual and Exhibition, 2018.
  26. Efficient classification of seismic textures. In 2018 International Joint Conference on Neural Networks (IJCNN), pages 1–8. IEEE, 2018.
  27. Augusto Cunha et al. Seismic fault detection in real data using transfer learning from a convolutional neural network pre-trained with synthetic seismic data. Computers & Geosciences, 135(10434):4, 2020.
  28. Learning transferable visual models from natural language supervision. In International conference on machine learning, pages 8748–8763. PMLR, 2021.
  29. Alex Krizhevsky. One weird trick for parallelizing convolutional neural networks. arXiv preprint arXiv:1404.5997, 2014.
  30. Kaiming He et al. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition p, pages 770–778, 2016.
  31. A convnet for the 2020s. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 11976–11986, 2022.
  32. Densely connected convolutional networks. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 4700–4708, 2017.
  33. Going deeper with convolutions. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 1–9, 2015.
  34. Rethinking the inception architecture for computer vision. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 2818–2826, 2016.
  35. Mnasnet: Platform-aware neural architecture search for mobile. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 2820–2828, 2019.
  36. Searching for mobilenetv3. In Proceedings of the IEEE/CVF international conference on computer vision, pages 1314–1324, 2019.
  37. Designing network design spaces. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 10428–10436, 2020.
  38. Aggregated residual transformations for deep neural networks. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 1492–1500, 2017.
  39. Shufflenet v2: Practical guidelines for efficient cnn architecture design. In Proceedings of the European conference on computer vision (ECCV), pages 116–131, 2018.
  40. Squeezenet: Alexnet-level accuracy with 50x fewer parameters and< 0.5 mb model size. arXiv preprint arXiv:1602.07360, 2016.
  41. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556, 2014.
  42. Wide residual networks. arXiv preprint arXiv:1605.07146, 2016.
  43. Pearson correlation coefficient. Noise reduction in speech processing, pages 1–4, 2009.
Citations (7)
View on Semantic Scholar

Summary

No one has generated a summary of this paper yet.

Sign Up to Summarize

Paper to Video (Beta)

No one has generated a video about this paper yet.

Sign Up to Generate All Videos Subscribe on YouTube

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Sign Up to Generate

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

Generate Now

Continue Learning

We haven't generated follow-up questions for this paper yet.

Generate Now

Collections

Sign up for free to add this paper to one or more collections.

Sign Up