Successfully reported this slideshow.
We use your LinkedIn profile and activity data to personalize ads and to show you more relevant ads. You can change your ad preferences anytime.

Image Classification on ImageNet (D1L3 Insight@DCU Machine Learning Workshop 2017)

758 views

Published on

https://github.com/telecombcn-dl/dlmm-2017-dcu

Deep learning technologies are at the core of the current revolution in artificial intelligence for multimedia data analysis. The convergence of big annotated data and affordable GPU hardware has allowed the training of neural networks for data analysis tasks which had been addressed until now with hand-crafted features. Architectures such as convolutional neural networks, recurrent neural networks and Q-nets for reinforcement learning have shaped a brand new scenario in signal processing. This course will cover the basic principles and applications of deep learning to computer vision problems, such as image classification, object detection or text captioning.

Published in: Data & Analytics
  • Be the first to comment

  • Be the first to like this

Image Classification on ImageNet (D1L3 Insight@DCU Machine Learning Workshop 2017)

  1. 1. Xavier Giro-i-Nieto xavier.giro@upc.edu Associate Professor Universitat Politecnica de Catalunya Technical University of Catalonia Image Classification on ImageNet #InsightDL2017
  2. 2. 2 ImageNet Challenge ● 1,000 object classes (categories). ● Images: ○ 1.2 M train ○ 100k test.
  3. 3. 3 Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., ... & Fei-Fei, L. (2015). Imagenet large scale visual recognition challenge. arXiv preprint arXiv:1409.0575. [web] ImageNet Dataset
  4. 4. Slide credit: Rob Fergus (NYU) -9.8% Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., ... & Fei-Fei, L. (2014). Imagenet large scale visual recognition challenge. arXiv preprint arXiv:1409.0575. [web] 4 Based on SIFT + Fisher Vectors ImageNet Challenge: 2012
  5. 5. AlexNet (Supervision) 5 Orange A Krizhevsky, I Sutskever, GE Hinton “Imagenet classification with deep convolutional neural networks” Part of: Advances in Neural Information Processing Systems 25 (NIPS 2012)
  6. 6. ImageNet Classification 2013 Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., ... & Fei-Fei, L. (2015). Imagenet large scale visual recognition challenge. arXiv preprint arXiv:1409.0575. [web] Slide credit: Rob Fergus (NYU) 6 ImageNet Challenge: 2013
  7. 7. The development of better convnets is reduced to trial-and-error. 7 Zeiler-Fergus (ZF) Visualization can help in proposing better architectures. Zeiler, M. D., & Fergus, R. (2014). Visualizing and understanding convolutional networks. In Computer Vision–ECCV 2014 (pp. 818-833). Springer International Publishing.
  8. 8. “A convnet model that uses the same components (filtering, pooling) but in reverse, so instead of mapping pixels to features does the opposite.” Zeiler, Matthew D., Graham W. Taylor, and Rob Fergus. "Adaptive deconvolutional networks for mid and high level feature learning." Computer Vision (ICCV), 2011 IEEE International Conference on. IEEE, 2011. 8 Zeiler-Fergus (ZF)
  9. 9. 9 Zeiler-Fergus (ZF) Zeiler, M. D., & Fergus, R. (2014). Visualizing and understanding convolutional networks. In Computer Vision–ECCV 2014 (pp. 818-833). Springer International Publishing. DeconvN et Conv Net
  10. 10. Zeiler, M. D., & Fergus, R. (2014). Visualizing and understanding convolutional networks. In Computer Vision–ECCV 2014 (pp. 818-833). Springer International Publishing. 10 Zeiler-Fergus (ZF)
  11. 11. Zeiler, M. D., & Fergus, R. (2014). Visualizing and understanding convolutional networks. In Computer Vision–ECCV 2014 (pp. 818-833). Springer International Publishing. 11 Zeiler-Fergus (ZF)
  12. 12. 12 Regularization with more dropout: introduced in the input layer. Hinton, G. E., Srivastava, N., Krizhevsky, A., Sutskever, I., & Salakhutdinov, R. R. (2012). Improving neural networks by preventing co-adaptation of feature detectors. arXiv preprint arXiv:1207.0580. Chicago Zeiler-Fergus (ZF): Drop out
  13. 13. 13 Zeiler-Fergus (ZF): Results
  14. 14. 14 Zeiler-Fergus (ZF): Results
  15. 15. ImageNet Classification 2013 Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., ... & Fei-Fei, L. (2015). Imagenet large scale visual recognition challenge. arXiv preprint arXiv:1409.0575. [web] -5% 15 ImageNet Challenge: 2013
  16. 16. 16NVIDIA, “NVIDIA and IBM CLoud Support ImageNet Large Scale Visual Recognition Challenge” (2015) ImageNet Challenge: 2014
  17. 17. 17 ImageNet Challenge: 2014
  18. 18. GoogLeNet (Inception) 18Movie: Inception (2010)
  19. 19. 19 ● 22 layers, but 12 times fewer parameters than AlexNet. Szegedy, Christian, Wei Liu, Yangqing Jia, Pierre Sermanet, Scott Reed, Dragomir Anguelov, Dumitru Erhan, Vincent Vanhoucke, and Andrew Rabinovich. "Going deeper with convolutions." GoogLeNet (Inception)
  20. 20. 20 GoogLeNet (Inception)
  21. 21. 21 Lin, Min, Qiang Chen, and Shuicheng Yan. "Network in network." ICLR 2014. GoogLeNet (Inception)
  22. 22. 22 Lin, Min, Qiang Chen, and Shuicheng Yan. "Network in network." ICLR 2014. Multiple scales GoogLeNet (Inception)
  23. 23. GoogLeNet (NiN) 23 3x3 and 5x5 convolutions deal with different scales. Lin, Min, Qiang Chen, and Shuicheng Yan. "Network in network." ICLR 2014. [Slides]
  24. 24. 24 Lin, Min, Qiang Chen, and Shuicheng Yan. "Network in network." ICLR 2014. Dimensionality reduction GoogLeNet (Inception)
  25. 25. 25 1x1 convolutions does dimensionality reduction (c3<c2) and accounts for rectified linear units (ReLU). Lin, Min, Qiang Chen, and Shuicheng Yan. "Network in network." ICLR 2014. [Slides] GoogLeNet (Inception)
  26. 26. 26 In GoogLeNet, the Cascaded 1x1 Convolutions compute reductions before the expensive 3x3 and 5x5 convolutions. GoogLeNet (Inception)
  27. 27. 27 Lin, Min, Qiang Chen, and Shuicheng Yan. "Network in network." ICLR 2014. GoogLeNet (Inception)
  28. 28. 28 They somewhat spatial invariance, and has proven a benefitial effect by adding an alternative parallel path. GoogLeNet (Inception)
  29. 29. 29 Two Softmax Classifiers at intermediate layers combat the vanishing gradient while providing regularization at training time. ...and no fully connected layers needed ! GoogLeNet (Inception)
  30. 30. 30 GoogLeNet (Inception)
  31. 31. 31 Szegedy, Christian, Wei Liu, Yangqing Jia, Pierre Sermanet, Scott Reed, Dragomir Anguelov, Dumitru Erhan, Vincent Vanhoucke, and Andrew Rabinovich. "Going deeper with convolutions." CVPR 2015. [video] [slides] [poster] GoogLeNet (Inception)
  32. 32. E2E: Classification: VGG 32 Simonyan, Karen, and Andrew Zisserman. "Very deep convolutional networks for large-scale image recognition." ICLR 2015. [video] [slides] [project]
  33. 33. E2E: Classification: VGG 33 Simonyan, Karen, and Andrew Zisserman. "Very deep convolutional networks for large-scale image recognition." International Conference on Learning Representations (2015). [video] [slides] [project]
  34. 34. E2E: Classification: VGG: 3x3 Stacks 34 Simonyan, Karen, and Andrew Zisserman. "Very deep convolutional networks for large-scale image recognition." International Conference on Learning Representations (2015). [video] [slides] [project]
  35. 35. E2E: Classification: VGG 35 Simonyan, Karen, and Andrew Zisserman. "Very deep convolutional networks for large-scale image recognition." International Conference on Learning Representations (2015). [video] [slides] [project] ● No poolings between some convolutional layers. ● Convolution strides of 1 (no skipping).
  36. 36. 36 3.6% top 5 error… with 152 layers !! ImageNet Challenge: 2015
  37. 37. E2E: Classification: ResNet 37 He, Kaiming, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. "Deep Residual Learning for Image Recognition." arXiv preprint arXiv:1512.03385 (2015). [slides]
  38. 38. E2E: Classification: ResNet 38 ● Deeper networks (34 is deeper than 18) are more difficult to train. He, Kaiming, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. "Deep Residual Learning for Image Recognition." arXiv preprint arXiv:1512.03385 (2015). [slides] Thin curves: training error Bold curves: validation error
  39. 39. ResNet 39 ● Residual learning: reformulate the layers as learning residual functions with reference to the layer inputs, instead of learning unreferenced functions He, Kaiming, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. "Deep Residual Learning for Image Recognition." arXiv preprint arXiv:1512.03385 (2015). [slides]
  40. 40. E2E: Classification: ResNet 40 He, Kaiming, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. "Deep Residual Learning for Image Recognition." arXiv preprint arXiv:1512.03385 (2015). [slides]
  41. 41. 41 Learn more Li Fei-Fei, “How we’re teaching computers to understand pictures” TEDTalks 2014. Russakovsky, O., Deng, J., Su, H., Krause, J., Satheesh, S., Ma, S., ... & Fei-Fei, L. (2015). Imagenet large scale visual recognition challenge. arXiv preprint arXiv:1409.0575. [web]
  42. 42. 42 Thanks ! Q&A ? Follow me at https://imatge.upc.edu/web/people/xavier-giro @DocXavi /ProfessorXavi

×