Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
139 tokens/sec
GPT-4o
47 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

FAGC:Feature Augmentation on Geodesic Curve in the Pre-Shape Space (2312.03325v3)

Published 6 Dec 2023 in cs.CV and cs.LG

Abstract: Deep learning has yielded remarkable outcomes in various domains. However, the challenge of requiring large-scale labeled samples still persists in deep learning. Thus, data augmentation has been introduced as a critical strategy to train deep learning models. However, data augmentation suffers from information loss and poor performance in small sample environments. To overcome these drawbacks, we propose a feature augmentation method based on shape space theory, i.e., feature augmentation on Geodesic curve, called FAGC in brevity.First, we extract features from the image with the neural network model. Then, the multiple image features are projected into a pre-shape space as features. In the pre-shape space, a Geodesic curve is built to fit the features. Finally, the many generated features on the Geodesic curve are used to train the various machine learning models. The FAGC module can be seamlessly integrated with most machine learning methods. And the proposed method is simple, effective and insensitive for the small sample datasets.Several examples demonstrate that the FAGC method can greatly improve the performance of the data preprocessing model in a small sample environment.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (72)
  1. Deep learning. nature, 521(7553):436–444, 2015.
  2. A survey of the usages of deep learning for natural language processing. IEEE transactions on neural networks and learning systems, 32(2):604–624, 2020.
  3. Automatic speech recognition: a survey. Multimedia Tools and Applications, 80:9411–9457, 2021.
  4. A survey on image data augmentation for deep learning. Journal of big data, 6(1):1–48, 2019.
  5. Nearest neighbor value interpolation. arXiv preprint arXiv:1211.1768, 2012.
  6. mixup: Beyond empirical risk minimization. arXiv preprint arXiv:1710.09412, 2017.
  7. Improved regularization of convolutional neural networks with cutout. arXiv preprint arXiv:1708.04552, 2017.
  8. Randaugment: Practical automated data augmentation with a reduced search space. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition workshops, pages 702–703, 2020.
  9. Generative adversarial nets. Advances in neural information processing systems, 27, 2014.
  10. Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114, 2013.
  11. V Terrance and W Taylor Graham. Dataset augmentation in feature space. In Proceedings of the international conference on machine learning (ICML), workshop track, volume 3, 2017.
  12. Smote: synthetic minority over-sampling technique. Journal of artificial intelligence research, 16:321–357, 2002.
  13. Dbsmote: density-based synthetic minority over-sampling technique. Applied Intelligence, 36:664–684, 2012.
  14. Manifold mixup: Better representations by interpolating hidden states. In International conference on machine learning, pages 6438–6447. PMLR, 2019.
  15. Implicit semantic data augmentation for deep networks. Advances in Neural Information Processing Systems, 32, 2019.
  16. David G Kendall. Shape manifolds, procrustean metrics, and complex projective spaces. Bulletin of the London mathematical society, 16(2):81–121, 1984.
  17. Shape and shape theory. John Wiley & Sons, 2009.
  18. DG Kendall. The diffusion of shape. 9 (3): 428-430. DOI: https://doi. org/10.2307/1426091, 1977.
  19. Object representation and recognition in shape spaces. Pattern recognition, 36(5):1143–1154, 2003.
  20. Robust models of object geometry. From Sensors to Human Spatial Concepts, page 59, 2006.
  21. Shape-space smoothing splines for planar landmark data. Biometrika, 94(3):513–528, 2007.
  22. Geometric modeling in shape space. In ACM SIGGRAPH 2007 papers, pages 64–es. 2007.
  23. Glass: Geometric latent augmentation for shape spaces. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 18552–18561, 2022.
  24. Recognizing objects with multiple configurations. Pattern Analysis and Applications, 17:195–209, 2014.
  25. Hide-and-seek: A data augmentation technique for weakly-supervised localization and beyond. arXiv preprint arXiv:1811.02545, 2018.
  26. Random erasing data augmentation. In Proceedings of the AAAI conference on artificial intelligence, volume 34, pages 13001–13008, 2020.
  27. Cutmix: Regularization strategy to train strong classifiers with localizable features. In Proceedings of the IEEE/CVF international conference on computer vision, pages 6023–6032, 2019.
  28. David G Lowe. Distinctive image features from scale-invariant keypoints. International journal of computer vision, 60:91–110, 2004.
  29. Histograms of oriented gradients for human detection. In 2005 IEEE computer society conference on computer vision and pattern recognition (CVPR’05), volume 1, pages 886–893. Ieee, 2005.
  30. Virus texture analysis using local binary patterns and radial density profiles. In Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications: 16th Iberoamerican Congress, CIARP 2011, Pucón, Chile, November 15-18, 2011. Proceedings 16, pages 573–580. Springer, 2011.
  31. A simple feature augmentation for domain generalization. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 8886–8895, 2021.
  32. On feature normalization and data augmentation. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 12383–12392, 2021.
  33. Hybrid cnn-svm classifier for handwritten digit recognition. Procedia Computer Science, 167:2554–2560, 2020.
  34. Christopher G Small. The statistical theory of shape. Springer Science & Business Media, 2012.
  35. IL Dryden and KV Mardia. Statistical shape analysis.,(wiley: New york, ny.). 1998.
  36. Recognition of multiple configurations of objects with limited data. Pattern Recognition, 43(4):1467–1475, 2010.
  37. Shape and shape theory. 1999.
  38. Christopher G Small. The statistical theory of shape. Springer Series in Statistics, 1996.
  39. Distributions of random shapes. The Statistical Theory of Shape, pages 149–172, 1996.
  40. Invariant object recognition by shape space analysis. In Proceedings 1998 International Conference on Image Processing. ICIP98 (Cat. No. 98CB36269), pages 581–585. IEEE, 1998.
  41. Yuexing Han. Recognize objects with three kinds of information in landmarks. Pattern Recognition, 46(11):2860–2873, 2013.
  42. Kim Evans. Curve-fitting in shape space. Quantitative biology, shape analysis, and wavelets. Leeds University Press, Leeds, 2005.
  43. Shape curves and geodesic modelling. Biometrika, 97(3):567–584, 2010.
  44. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929, 2020.
  45. Learning multiple layers of features from tiny images. 2009.
  46. Comatch: Semi-supervised learning with contrastive graph regularization. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 9475–9484, 2021.
  47. Semi-supervised learning with ladder networks. Advances in neural information processing systems, 28, 2015.
  48. Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results. Advances in neural information processing systems, 30, 2017.
  49. Dong-Hyun Lee et al. Pseudo-label: The simple and efficient semi-supervised learning method for deep neural networks. In Workshop on challenges in representation learning, ICML, volume 3, page 896. Atlanta, 2013.
  50. Mixmatch: A holistic approach to semi-supervised learning. Advances in neural information processing systems, 32, 2019.
  51. Virtual adversarial training: a regularization method for supervised and semi-supervised learning. IEEE transactions on pattern analysis and machine intelligence, 41(8):1979–1993, 2018.
  52. Dash: Semi-supervised learning with dynamic thresholding. In International Conference on Machine Learning, pages 11525–11536. PMLR, 2021.
  53. Revisiting consistency regularization for semi-supervised learning. International Journal of Computer Vision, 131(3):626–643, 2023.
  54. Unsupervised data augmentation for consistency training. Advances in neural information processing systems, 33:6256–6268, 2020.
  55. Fixmatch: Simplifying semi-supervised learning with consistency and confidence. Advances in neural information processing systems, 33:596–608, 2020.
  56. Flexmatch: Boosting semi-supervised learning with curriculum pseudo labeling. Advances in Neural Information Processing Systems, 34:18408–18419, 2021.
  57. Freematch: Self-adaptive thresholding for semi-supervised learning. arXiv preprint arXiv:2205.07246, 2022.
  58. Adamatch: A unified approach to semi-supervised learning and domain adaptation. arXiv preprint arXiv:2106.04732, 2021.
  59. Simmatch: Semi-supervised learning with similarity matching. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 14471–14481, 2022.
  60. Softmatch: Addressing the quantity-quality trade-off in semi-supervised learning. arXiv preprint arXiv:2301.10921, 2023.
  61. Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101, 2017.
  62. Usb: A unified semi-supervised learning benchmark. arXiv preprint arXiv:2208.07204, 2022.
  63. Wide residual networks. arXiv preprint arXiv:1605.07146, 2016.
  64. Augmix: A simple data processing method to improve robustness and uncertainty. arXiv preprint arXiv:1912.02781, 2019.
  65. Nearest neighbor pattern classification. IEEE transactions on information theory, 13(1):21–27, 1967.
  66. Support-vector networks. Machine learning, 20:273–297, 1995.
  67. J. Ross Quinlan. Induction of decision trees. Machine learning, 1:81–106, 1986.
  68. Extremely randomized trees. Machine learning, 63:3–42, 2006.
  69. Leo Breiman. Random forests. Machine learning, 45:5–32, 2001.
  70. Leo Breiman. Bagging predictors. Machine learning, 24:123–140, 1996.
  71. Jerome H Friedman. Greedy function approximation: a gradient boosting machine. Annals of statistics, pages 1189–1232, 2001.
  72. Learning representations by back-propagating errors. nature, 323(6088):533–536, 1986.
Citations (5)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now