Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
184 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Efficient CNN with uncorrelated Bag of Features pooling (2209.10865v1)

Published 22 Sep 2022 in cs.CV

Abstract: Despite the superior performance of CNN, deploying them on low computational power devices is still limited as they are typically computationally expensive. One key cause of the high complexity is the connection between the convolution layers and the fully connected layers, which typically requires a high number of parameters. To alleviate this issue, Bag of Features (BoF) pooling has been recently proposed. BoF learns a dictionary, that is used to compile a histogram representation of the input. In this paper, we propose an approach that builds on top of BoF pooling to boost its efficiency by ensuring that the items of the learned dictionary are non-redundant. We propose an additional loss term, based on the pair-wise correlation of the items of the dictionary, which complements the standard loss to explicitly regularize the model to learn a more diverse and rich dictionary. The proposed strategy yields an efficient variant of BoF and further boosts its performance, without any additional parameters.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (52)
  1. “Deep learning,” nature, vol. 521, no. 7553, pp. 436–444, 2015.
  2. Ross Girshick, “Fast r-cnn,” in Proceedings of the IEEE international conference on computer vision, 2015, pp. 1440–1448.
  3. “Imagenet classification with deep convolutional neural networks,” Advances in neural information processing systems, vol. 25, 2012.
  4. “Deep residual learning for image recognition,” in Proceedings of the IEEE conference on computer vision and pattern recognition, 2016, pp. 770–778.
  5. “Very deep convolutional networks for large-scale image recognition,” arXiv preprint arXiv:1409.1556, 2014.
  6. “Faster r-cnn: Towards real-time object detection with region proposal networks,” Advances in neural information processing systems, vol. 28, 2015.
  7. “Object detection with deep learning: A review,” IEEE transactions on neural networks and learning systems, vol. 30, no. 11, pp. 3212–3232, 2019.
  8. “Efficientdet: Scalable and efficient object detection,” in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2020, pp. 10781–10790.
  9. “Deep learning for anomaly detection: Challenges, methods, and opportunities,” in Proceedings of the 14th ACM International Conference on Web Search and Data Mining, 2021, pp. 1127–1130.
  10. “Deep one-class classification,” in International conference on machine learning. PMLR, 2018, pp. 4393–4402.
  11. “Learning memory-guided normality for anomaly detection,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 14372–14381.
  12. “An encoding technique for cnn-based network anomaly detection,” in 2018 IEEE International Conference on Big Data (Big Data). IEEE, 2018, pp. 2960–2965.
  13. “Deep learning with edge computing: A review,” Proceedings of the IEEE, vol. 107, no. 8, pp. 1655–1674, 2019.
  14. “Color constancy convolutional autoencoder,” in 2019 IEEE Symposium Series on Computational Intelligence (SSCI). IEEE, 2019, pp. 1085–1090.
  15. Deep learning, MIT press, 2016.
  16. “Exploiting kernel sparsity and entropy for interpretable cnn compression,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2019.
  17. “Towards convolutional neural networks compression via global error reconstruction.,” in IJCAI, 2016, pp. 1753–1759.
  18. “Neural bag-of-features learning,” Pattern Recognition, pp. 277–294, 2017.
  19. “Learning bag-of-features pooling for deep convolutional neural networks,” in IEEE International Conference on Computer Vision, 2017.
  20. Gaurav Menghani, “Efficient deep learning: A survey on making deep learning models smaller, faster, and better,” arXiv preprint arXiv:2106.08962, 2021.
  21. “A bayesian hierarchical model for learning natural scene categories,” in IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2005, pp. 524–531.
  22. G. Qiu, “Indexing chromatic and achromatic patterns for content-based colour image retrieval,” Pattern Recognition, pp. 1675 – 1686, 2002.
  23. “Evaluating bag-of-visual-words representations in scene classification,” in Proceedings of the international workshop on Workshop on multimedia information retrieval, 2007, pp. 197–206.
  24. “Fisher vectors: Beyond bag-of-visual-words image representations,” in International Conference on Computer Vision, Imaging and Computer Graphics. Springer, 2010, pp. 28–42.
  25. “Bag of visual words methodology in remote sensing—a review,” in Proceedings of the International e-Conference on Intelligent Systems and Signal processing. Springer, 2022, pp. 475–486.
  26. “Understanding bag-of-words model: a statistical framework,” International journal of machine learning and cybernetics, vol. 1, no. 1, pp. 43–52, 2010.
  27. “Training lightweight deep convolutional neural networks using bag-of-features pooling,” IEEE transactions on neural networks and learning systems, vol. 30, no. 6, pp. 1705–1715, 2018.
  28. “Self-attention neural bag-of-features,” arXiv preprint arXiv:2201.11092, 2022.
  29. “Temporal bag-of-features learning for predicting mid price movements using high frequency limit order book data,” IEEE Transactions on Emerging Topics in Computational Intelligence, vol. 4, no. 6, pp. 774–785, 2020.
  30. “Discriminant bag of words based representation for human action recognition,” Pattern Recognition Letters, pp. 185 – 192, 2014.
  31. “Efficient adaptive inference for deep convolutional neural networks using hierarchical early exits,” Pattern Recognition, vol. 105, pp. 107346, 2020.
  32. “Attention-based neural bag-of-features learning for sequence data,” arXiv preprint arXiv:2005.12250, 2020.
  33. “Towards optimal bag-of-features for object categorization and semantic video retrieval,” in ACM International Conference on Image and Video Retrieval, 2007, pp. 494–501.
  34. “Bag of color features for color constancy,” IEEE Transactions on Image Processing, vol. 29, pp. 7722–7734, 2020.
  35. Huanhuan Chen, Diversity and regularization in neural network ensembles, Ph.D. thesis, University of Birmingham, 2008.
  36. “Supervised dictionary learning and sparse representation-a review,” arXiv preprint arXiv:1502.05928, 2015.
  37. K Rajesh and Atul Negi, “Heuristic based learning of parameters for dictionaries in sparse representations,” in 2018 IEEE Symposium Series on Computational Intelligence (SSCI). IEEE, 2018, pp. 1013–1019.
  38. “Regularizing deep neural networks by enhancing diversity in feature extraction,” IEEE transactions on neural networks and learning systems, vol. 30, no. 9, pp. 2650–2661, 2019.
  39. “Correlation based online dictionary learning algorithm,” IEEE Transactions on signal processing, vol. 64, no. 3, pp. 592–602, 2015.
  40. “Kernel dictionary learning,” in 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2012, pp. 2021–2024.
  41. “Uncorrelated multi-view discrimination dictionary learning for recognition,” in Proceedings of the AAAI Conference on Artificial Intelligence, 2014, vol. 28.
  42. “Orthogonal convolutional neural networks,” in Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2020, pp. 11505–11515.
  43. “Barlow twins: Self-supervised learning via redundancy reduction,” in International Conference on Machine Learning. PMLR, 2021, pp. 12310–12320.
  44. “Uncorrelation and evenness: a new diversity-promoting regularizer,” in Proceedings of the 34th International Conference on Machine Learning, 2017, pp. 3811–3820.
  45. “Reducing overfitting in deep networks by decorrelating representations,” arXiv preprint arXiv:1511.06068, 2015.
  46. “On feature diversity in energy-based models,” in Energy Based Models Workshop-ICLR 2021, 2021.
  47. “Reducing redundancy in the bottleneck representation of the autoencoders,” arXiv preprint arXiv:2202.04629, 2022.
  48. “Within-layer diversity reduces generalization gap,” arXiv preprint arXiv:2106.06012, 2021.
  49. “Gradient-based learning applied to document recognition,” Proceedings of the IEEE, vol. 86, no. 11, pp. 2278–2324, 1998.
  50. “Fashion-mnist: a novel image dataset for benchmarking machine learning algorithms,” arXiv preprint arXiv:1708.07747, 2017.
  51. “Learning multiple layers of features from tiny images,” 2009.
  52. “Adam: A method for stochastic optimization,” arXiv preprint arXiv:1412.6980, 2014.
Citations (2)
View on Semantic Scholar

Summary

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

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