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

One-Shot Multi-Rate Pruning of Graph Convolutional Networks (2312.17615v1)

Published 29 Dec 2023 in cs.CV

Abstract: In this paper, we devise a novel lightweight Graph Convolutional Network (GCN) design dubbed as Multi-Rate Magnitude Pruning (MRMP) that jointly trains network topology and weights. Our method is variational and proceeds by aligning the weight distribution of the learned networks with an a priori distribution. In the one hand, this allows implementing any fixed pruning rate, and also enhancing the generalization performances of the designed lightweight GCNs. In the other hand, MRMP achieves a joint training of multiple GCNs, on top of shared weights, in order to extrapolate accurate networks at any targeted pruning rate without retraining their weights. Extensive experiments conducted on the challenging task of skeleton-based recognition show a substantial gain of our lightweight GCNs particularly at very high pruning regimes.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (135)
  1. Variational information distillation for knowledge transfer. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 9163–9171, 2019.
  2. H. Sahbi and N. Boujemaa. ”From coarse to fine skin and face detection.” Proceedings of the eighth ACM international conference on Multimedia. 2000.
  3. Spectral networks and locally connected networks on graphs. arXiv preprint arXiv:1312.6203, 2013.
  4. Once-for-all: Train one network and specialize it for efficient deployment. arXiv preprint arXiv:1908.09791, 2019.
  5. H. Sahbi and F. Fleuret. Scale-invariance of support vector machines based on the triangular kernel. Diss. INRIA, 2002.
  6. Realtime multi-person 2d pose estimation using part affinity fields. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 7291–7299, 2017.
  7. “learning-compression” algorithms for neural net pruning. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 8532–8541, 2018.
  8. Motion feature augmented recurrent neural network for skeleton-based dynamic hand gesture recognition. In 2017 IEEE International Conference on Image Processing (ICIP), pages 2881–2885. IEEE, 2017.
  9. Construct dynamic graphs for hand gesture recognition via spatial-temporal attention. arXiv preprint arXiv:1907.08871, 2019.
  10. Fan RK Chung. Spectral graph theory, volume 92. American Mathematical Soc., 1997.
  11. M. Ferecatu and H. Sahbi. ”Multi-view object matching and tracking using canonical correlation analysis.” 2009 16th IEEE International Conference on Image Processing (ICIP). IEEE, 2009.
  12. Convolutional neural networks on graphs with fast localized spectral filtering. Advances in neural information processing systems, 29, 2016.
  13. Hierarchical recurrent neural network for skeleton based action recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 1110–1118, 2015.
  14. Convolutional two-stream network fusion for video action recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 1933–1941, 2016.
  15. Transition forests: Learning discriminative temporal transitions for action recognition and detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 432–440, 2017.
  16. H. Sahbi. ”Misalignment resilient cca for interactive satellite image change detection.” 2016 23rd International Conference on Pattern Recognition (ICPR). IEEE, 2016.
  17. First-person hand action benchmark with rgb-d videos and 3d hand pose annotations. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 409–419, 2018.
  18. Morphnet: Fast & simple resource-constrained structure learning of deep networks. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 1586–1595, 2018.
  19. A new model for learning in graph domains. In Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005., volume 2, pages 729–734. IEEE, 2005.
  20. T. Napoléon and H. Sahbi. ”From 2D silhouettes to 3D object retrieval: contributions and benchmarking.” EURASIP Journal on Image and Video Processing 2010 (2010): 1-17.
  21. Inductive representation learning on large graphs. Advances in neural information processing systems, 30, 2017.
  22. Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding. arXiv preprint arXiv:1510.00149, 2015.
  23. Learning both weights and connections for efficient neural network. Advances in neural information processing systems, 28, 2015.
  24. Second order derivatives for network pruning: Optimal brain surgeon. Advances in neural information processing systems, 5, 1992.
  25. Mask r-cnn. In Proceedings of the IEEE international conference on computer vision, pages 2961–2969, 2017.
  26. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 770–778, 2016.
  27. Soft filter pruning for accelerating deep convolutional neural networks. arXiv preprint arXiv:1808.06866, 2018.
  28. Amc: Automl for model compression and acceleration on mobile devices. In Proceedings of the European conference on computer vision (ECCV), pages 784–800, 2018.
  29. Deep convolutional networks on graph-structured data. arXiv preprint arXiv:1506.05163, 2015.
  30. Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531, 2015.
  31. Spatial-temporal attention res-tcn for skeleton-based dynamic hand gesture recognition. In Proceedings of the European conference on computer vision (ECCV) workshops, pages 0–0, 2018.
  32. Searching for mobilenetv3. In Proceedings of the IEEE/CVF international conference on computer vision, pages 1314–1324, 2019.
  33. Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861, 2017.
  34. Jointly learning heterogeneous features for rgb-d activity recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 5344–5352, 2015.
  35. Condensenet: An efficient densenet using learned group convolutions. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 2752–2761, 2018.
  36. H. Sahbi. ”Imageclef annotation with explicit context-aware kernel maps.” International Journal of Multimedia Information Retrieval 4.2 (2015): 113-128.
  37. A riemannian network for spd matrix learning. In Proceedings of the AAAI conference on artificial intelligence, volume 31, 2017.
  38. Deep learning on lie groups for skeleton-based action recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 6099–6108, 2017.
  39. Building deep networks on grassmann manifolds. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 32, 2018.
  40. H. Sahbi. ”CNRS-TELECOM ParisTech at ImageCLEF 2013 Scalable Concept Image Annotation Task: Winning Annotations with Context Dependent SVMs.” CLEF (Working Notes). 2013.
  41. Interactive body part contrast mining for human interaction recognition. In 2014 IEEE international conference on multimedia and expo workshops (ICMEW), pages 1–6. IEEE, 2014.
  42. Densely connected convolutional network optimized by genetic algorithm for fingerprint liveness detection. IEEE Access, 9:2229–2243, 2020.
  43. H. Sahbi. A particular Gaussian mixture model for clustering and its application to image retrieval. Soft Computing 12 (7), 667-676
  44. Deep representation design from deep kernel networks. Pattern Recognition, 88:447–457, 2019.
  45. A novel geometric framework on gram matrix trajectories for human behavior understanding. IEEE transactions on pattern analysis and machine intelligence, 42(1):1–14, 2018.
  46. A new representation of skeleton sequences for 3d action recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 3288–3297, 2017.
  47. A. Mazari and H. Sahbi. ”MLGCN: Multi-Laplacian graph convolutional networks for human action recognition.” The British Machine Vision Conference (BMVC). 2019.
  48. Intel realsense stereoscopic depth cameras. In Proceedings of the IEEE conference on computer vision and pattern recognition workshops, pages 1–10, 2017.
  49. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980, 2014.
  50. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907, 2016.
  51. M. Ferecatu and H. Sahbi. ”TELECOM ParisTech at ImageClefphoto 2008: Bi-Modal Text and Image Retrieval with Diversity Enhancement.” CLEF (Working Notes). 2008.
  52. Understanding attention and generalization in graph neural networks. Advances in neural information processing systems, 32, 2019.
  53. Basava Naga Girish Koneru and Vinita Vasudevan. Sparse artificial neural networks using a novel smoothed lasso penalization. IEEE Transactions on Circuits and Systems II: Express Briefs, 66(5):848–852, 2019.
  54. Imagenet classification with deep convolutional neural networks. Communications of the ACM, 60(6):84–90, 2017.
  55. Optimal brain damage. Advances in neural information processing systems, 2, 1989.
  56. Ensemble deep learning for skeleton-based action recognition using temporal sliding lstm networks. In Proceedings of the IEEE international conference on computer vision, pages 1012–1020, 2017.
  57. Structured pruning of neural networks with budget-aware regularization. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 9108–9116, 2019.
  58. H. Sahbi. ”Coarse-to-fine deep kernel networks.” IEEE ICCV-W, 2017.
  59. Cayleynets: Graph convolutional neural networks with complex rational spectral filters. IEEE Transactions on Signal Processing, 67(1):97–109, 2018.
  60. Spatio-temporal graph routing for skeleton-based action recognition. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 33, pages 8561–8568, 2019.
  61. M. Jiu and H. Sahbi. ”Laplacian deep kernel learning for image annotation.” IEEE ICASSP, 2016.
  62. Spatio-temporal graph convolution for skeleton based action recognition. In Proceedings of the AAAI conference on artificial intelligence, volume 32, 2018.
  63. Pruning filters for efficient convnets. arXiv preprint arXiv:1608.08710, 2016.
  64. Adaptive graph convolutional neural networks. In Proceedings of the AAAI conference on artificial intelligence, volume 32, 2018.
  65. N. Bourdis, D. Marraud and H. Sahbi. ”Camera pose estimation using visual servoing for aerial video change detection.” IEEE IGARSS 2012.
  66. Global co-occurrence feature learning and active coordinate system conversion for skeleton-based action recognition. In Proceedings of the IEEE/CVF winter conference on applications of computer vision, pages 586–594, 2020.
  67. Category-blind human action recognition: A practical recognition system. In Proceedings of the IEEE international conference on computer vision, pages 4444–4452, 2015.
  68. H. Sahbi and N. Boujemaa. ”Robust matching by dynamic space warping for accurate face recognition.” Proceedings 2001 International Conference on Image Processing (Cat. No. 01CH37205). Vol. 1. IEEE, 2001.
  69. Decoupled representation learning for skeleton-based gesture recognition. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 5751–5760, 2020.
  70. Han: An efficient hierarchical self-attention network for skeleton-based gesture recognition. arXiv preprint arXiv:2106.13391, 2021.
  71. Spatio-temporal lstm with trust gates for 3d human action recognition. In Computer Vision–ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11-14, 2016, Proceedings, Part III 14, pages 816–833. Springer, 2016.
  72. Skeleton-based human action recognition with global context-aware attention lstm networks. IEEE Transactions on Image Processing, 27(4):1586–1599, 2017.
  73. Q. Oliveau and H. Sahbi. ”Learning attribute representations for remote sensing ship category classification.” IEEE JSTARS 10.6 (2017): 2830-2840.
  74. Global context-aware attention lstm networks for 3d action recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 1647–1656, 2017.
  75. Enhanced skeleton visualization for view invariant human action recognition. Pattern Recognition, 68:346–362, 2017.
  76. Recognizing human actions as the evolution of pose estimation maps. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 1159–1168, 2018.
  77. Learning efficient convolutional networks through network slimming. In Proceedings of the IEEE international conference on computer vision, pages 2736–2744, 2017.
  78. Learning sparse neural networks through l⁢_⁢0𝑙_0l\_0italic_l _ 0 regularization. arXiv preprint arXiv:1712.01312, 2017.
  79. H. Sahbi. ”Relevance feedback for satellite image change detection.” IEEE ICASSP, 2013.
  80. Deepgru: Deep gesture recognition utility. In Advances in Visual Computing: 14th International Symposium on Visual Computing, ISVC 2019, Lake Tahoe, NV, USA, October 7–9, 2019, Proceedings, Part I 14, pages 16–31. Springer, 2019.
  81. Deep temporal pyramid design for action recognition. In IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 2077–2081. IEEE, 2019.
  82. Mlgcn: Multi-laplacian graph convolutional networks for human action recognition. In The British Machine Vision Conference (BMVC), 2019.
  83. Linear-time online action detection from 3d skeletal data using bags of gesturelets. In 2016 IEEE winter conference on applications of computer vision (WACV), pages 1–9. IEEE, 2016.
  84. Alessio Micheli. Neural network for graphs: A contextual constructive approach. IEEE Transactions on Neural Networks, 20(3):498–511, 2009.
  85. Improved knowledge distillation via teacher assistant. In Proceedings of the AAAI conference on artificial intelligence, volume 34, pages 5191–5198, 2020.
  86. A neural network based on spd manifold learning for skeleton-based hand gesture recognition. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 12036–12045, 2019.
  87. Convolutional neural networks and long short-term memory for skeleton-based human activity and hand gesture recognition. Pattern Recognition, 76:80–94, 2018.
  88. Hand gesture recognition in real time for automotive interfaces: A multimodal vision-based approach and evaluations. IEEE transactions on intelligent transportation systems, 15(6):2368–2377, 2014.
  89. Hichem Sahbi. Kernel-based graph convolutional networks. In 25th International Conference on Pattern Recognition (ICPR), pages 4887–4894. IEEE, 2021.
  90. Hon4d: Histogram of oriented 4d normals for activity recognition from depth sequences. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 716–723, 2013.
  91. Dropneuron: Simplifying the structure of deep neural networks. arXiv preprint arXiv:1606.07326, 2016.
  92. Hichem Sahbi. Learning connectivity with graph convolutional networks. In 25th International Conference on Pattern Recognition (ICPR), pages 9996–10003. IEEE, 2021.
  93. Skeleton-based dynamic hand gesture recognition. Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit. Workshops (CVPRW), Las Vegas, NV, United states, june, pp 1206-1214, 2016.
  94. 3d action recognition from novel viewpoints. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 1506–1515, 2016.
  95. U-net: Convolutional networks for biomedical image segmentation. In Medical Image Computing and Computer-Assisted Intervention–MICCAI 2015: 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part III 18, pages 234–241. Springer, 2015.
  96. Hichem Sahbi. Kernel pca for similarity invariant shape recognition. Neurocomputing, 70(16-18):3034–3045, 2007.
  97. Mobilenetv2: Inverted residuals and linear bottlenecks. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 4510–4520, 2018.
  98. Ntu rgb+ d: A large scale dataset for 3d human activity analysis. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 1010–1019, 2016.
  99. Hichem Sahbi. Learning laplacians in chebyshev graph convolutional networks. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 2064–2075, 2021.
  100. Non-local graph convolutional networks for skeleton-based action recognition. arXiv preprint arXiv:1805.07694, 1(2):3, 2018.
  101. An end-to-end spatio-temporal attention model for human action recognition from skeleton data. In Proceedings of the AAAI conference on artificial intelligence, volume 31, 2017.
  102. Efficientnet: Rethinking model scaling for convolutional neural networks. In International conference on machine learning, pages 6105–6114. PMLR, 2019.
  103. Hichem Sahbi. Lightweight connectivity in graph convolutional networks for skeleton-based recognition. In IEEE International Conference on Image Processing (ICIP), pages 2329–2333. IEEE, 2021.
  104. Human action recognition by representing 3d skeletons as points in a lie group. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 588–595, 2014.
  105. Regularization of neural networks using dropconnect. In International conference on machine learning, pages 1058–1066. PMLR, 2013.
  106. Modeling temporal dynamics and spatial configurations of actions using two-stream recurrent neural networks. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 499–508, 2017.
  107. Directed acyclic graph kernels for action recognition. In Proceedings of the IEEE International Conference on Computer Vision, pages 3168–3175, 2013.
  108. Bags-of-daglets for action recognition. In IEEE International Conference on Image Processing (ICIP), pages 1550–1554. IEEE, 2014.
  109. Action recognition from depth maps using deep convolutional neural networks. IEEE Transactions on Human-Machine Systems, 46(4):498–509, 2015.
  110. Rgb-d-based human motion recognition with deep learning: A survey. Computer Vision and Image Understanding, 171:118–139, 2018.
  111. Hichem Sahbi. Topologically-consistent magnitude pruning for very lightweight graph convolutional networks. In IEEE International Conference on Image Processing (ICIP), pages 3495–3499. IEEE, 2022.
  112. Action recognition based on joint trajectory maps using convolutional neural networks. In Proceedings of the 24th ACM international conference on Multimedia, pages 102–106, 2016.
  113. Learning structured sparsity in deep neural networks. Advances in neural information processing systems, 29, 2016.
  114. Graph cnns with motif and variable temporal block for skeleton-based action recognition. In Proceedings of the AAAI conference on artificial intelligence, volume 33, pages 8989–8996, 2019.
  115. Hichem Sahbi. Phase-field models for lightweight graph convolutional networks. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 4643–4649, 2023.
  116. Deformable pose traversal convolution for 3d action and gesture recognition. In Proceedings of the European conference on computer vision (ECCV), pages 136–152, 2018.
  117. Entropy-constrained training of deep neural networks. In 2019 International Joint Conference on Neural Networks (IJCNN), pages 1–8. IEEE, 2019.
  118. Context-dependent kernels for object classification. IEEE transactions on pattern analysis and machine intelligence, 33(4):699–708, 2011.
  119. A comprehensive survey on graph neural networks. IEEE transactions on neural networks and learning systems, 32(1):4–24, 2020.
  120. View invariant human action recognition using histograms of 3d joints. In 2012 IEEE computer society conference on computer vision and pattern recognition workshops, pages 20–27. IEEE, 2012.
  121. Spatial temporal graph convolutional networks for skeleton-based action recognition. In Proceedings of the AAAI conference on artificial intelligence, volume 32, 2018.
  122. Kernel methods and scale invariance using the triangular kernel. Technical report, INRIA, 2004.
  123. Effective 3d action recognition using eigenjoints. Journal of Visual Communication and Image Representation, 25(1):2–11, 2014.
  124. Mid-level features and spatio-temporal context for activity recognition. Pattern Recognition, 45(12):4182–4191, 2012.
  125. Two-person interaction detection using body-pose features and multiple instance learning. In 2012 IEEE computer society conference on computer vision and pattern recognition workshops, pages 28–35. IEEE, 2012.
  126. The moving pose: An efficient 3d kinematics descriptor for low-latency action recognition and detection. In Proceedings of the IEEE international conference on computer vision, pages 2752–2759, 2013.
  127. A hierarchy of support vector machines for pattern detection. Journal of Machine Learning Research, 7(10), 2006.
  128. View adaptive recurrent neural networks for high performance human action recognition from skeleton data. In Proceedings of the IEEE international conference on computer vision, pages 2117–2126, 2017.
  129. On geometric features for skeleton-based action recognition using multilayer lstm networks. In 2017 IEEE Winter Conference on Applications of Computer Vision (WACV), pages 148–157. IEEE, 2017.
  130. Nonlinear deep kernel learning for image annotation. IEEE Transactions on Image Processing, 26(4):1820–1832, 2017.
  131. Efficient temporal sequence comparison and classification using gram matrix embeddings on a riemannian manifold. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 4498–4507, 2016.
  132. Deep mutual learning. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 4320–4328, 2018.
  133. Deep learning on graphs: A survey. IEEE Transactions on Knowledge and Data Engineering, 34(1):249–270, 2020.
  134. Co-occurrence feature learning for skeleton based action recognition using regularized deep lstm networks. In Proceedings of the AAAI conference on artificial intelligence, volume 30, 2016.
  135. P. Vo and H. Sahbi. ”Transductive kernel map learning and its application to image annotation.” BMVC. 2012.

Summary

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

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