Description:

Dr. Qi has kept some of his research interests by collaboratively working with Professor Jack Xin at the University of California, Irvine after joining Qualcomm. The collaboration has produced a number of publications. Recent publications are focused modeling, optimization, and computing with applications to machine learning. Some earlier publications on neural networks are also listed here, providing a background on this tract of work.

Publications :

• Z. Li, B. Yang, P. Yin, Y. Qi, and J. Xin, Feature Affinity Assisted Knowledge Distillation and Quantization of Deep Neural Networks on Label-Free Data, IEEE Access, Vol 11, pp. 78042-78051, 2023. DOI:10.1109/ACCESS.2023.3297890
• K. Bui, F. Xue, F. Park, Y. Qi, and J. Xin, A Proximal Algorithm for Network Slimming, Proc. of the 9th International Conference on Machine Learning, Optimization and Data Science, Grasmere, Lake District, England, Sept, 2023.
• F. Xue, Y. Qi, and J. Xin, RARTS: An Efficient First-Order Relaxed Architecture Search Method, IEEE ACCESS, 2022, doi:10.1109/ACCESS.2022.3185095.
• F. Xue, B. Yang, Y. Qi, and J. Xin, Searching Intrinsic Dimensions of Vision Transformers, in Proc. of the Porto 20th International Conference on Innovations in Engineering and Sciences, pp. 18-24, 2022.
• B. Yang, F. Xue, Y. Qi. and J. Xin, Improving Efficient Semantic Segmentation Networks by Enhancing Multi-Scale Feature Representation via Resolution Path Based Knowledge Distillation and Pixel Shuffle, pp. 325-336, in Proc. of the 16th International Symposium on Visual Computing, Oct, 2021.
• K. Bui, F. Park, S. Zhang, Y.Qi, and J. Xin, Structured sparsity of convolutional neural networks via nonconvex sparse group regularization. Frontiers in Applied Mathematics and Statistics, 2021
• K. Bui, F. Park, S. Zhang, Y. Qi. J. Xin, Improving Network Slimming with Nonconvex Regularization, IEEE Access, Vol. 9, pp. 115292-115314, 2021.
• J. Lyu, S. Zhang, Y. Qi. J. Xin. AutoShuffleNet: Learning Permutation Matrices via an Exact Lipschitz Continuous Penalty in Deep Convolutional Neural Networks. In Proceedings of the 26th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2020).
• K. Bui, F. Park, S. Zhang, Y. Qi, J. Xin. Nonconvex Regularization for Network Slimming: Compressing CNNs Even More. Awarded Springer-Verlag Best Paper at the 15th International Symposium on Visual Computing, 2020.
• Y. Xu, Y. Li, S. Zhang, W. Wen, B. Wang, Y. Qi, Y. Chen, W. Lin, H. Xiong, TRP: Trained Rank Pruning for Efficient Deep Neural Networks, International Joint Conference on Artificial Intelligence (IJCAI), 2020.
• Y. Xu, W. Dai, Y. Qi, J. Zou, H. Xiong Iterative Deep Neural Network Quantization with Lipschitz Constraint, IEEE Transactions on Multimedia, Online ISSN: 1941-0077 Digital Object Identifier: 10.1109/TMM.2019.2949857, 2020
• Y. Xu, Y. Li, S. Zhang, W. Wen, B. Wang, W. Dai, Y. Qi, Y. Chen, W. Lin, H. Xiong, Trained Rank Pruning for Efficient Deep Neural Networks, Workshop on Energy Efficient Machine Learning and Cognitive Computing, Neural Information Processing Systems (NIPS), Vancouver, 2019.
• E. Mequanint, S. Zhang, Y. QI, and N. Bi, Weakly-supervised Degree of Eye-Closeness Estimation, EPIC Workshop at International Conference on Computer Vsion (ICCV), Seoul, 2019.
• B. Yang, J. Xin, J. Lyu, S. Zhang, and Y. QI, Channel Pruning for Deep Neural Networks via a Relaxed Groupwise Splitting Method, IEEE Artificial Intelligence for Industries (AI4I), Laguna Hill, California, 2019.
• B. Yang, J. Xin, J. Lyu, S. Zhang, and Y. QI, A Multistage Backward Differentiable Method for Constructing Light Convolutional Neural Networks, IEEE Artificial Intelligence for Industries (AI4I), Laguna Hill, California, 2019.
• P. Yin, S. Zhang, J. Lyu, S. Osher, Y. Qi, and J. Xin. Blended Coarse Gradient Descent for Full Quantization of Deep Neural Networks. Research in the Mathematical Sciences, Springer, 2019
• P. Yin, S. Zhang, J. Lyu, S. Osher, Y. Qi, and J. Xin. Understanding Straight-Through Estimator in Training Activation Quantized Neural Nets. International Conference on Learning Representations (ICLR), New Orleans, 2019
• Y. Xu, S. Zhang, Y. Qi, J. Guo, W. Lin, H. Xiong DNQ: Dynamic Network Quantization IEEE Data Compression Conference, Utah, 2019.
• X. Li, S. Zhang, B. Jiang, Y. Qi, M. Chuah, and N. Bi. DAC: Data-free Automatic Acceleration of Convolutional Networks. IEEE Winter Conference on Applications of Computer Vision, Hawaii, 2019.
• P. Yin , S. Zhang, J. Lyu , S. Osher, Y. Qi , and J. Xin, BinaryRelax: A Relaxation Approach For Training Deep Neural Networks With Quantized Weights. SIAM Journal on Imaging Sciences, 11(4), 2205–2223, 2018
• P. Yin, S. Zhang, Y. Qi, and J. Xin. Quantization and Training of Low Bit-Width Convolutional Neural Networks for Object Detection. Journal of Computational Mathematics, 37(3):349 - 360, 2018.
• P. Yin, J. Xin, and Y. Qi. Linear Feature Transform and Enhancement of Classification on Deep Neural Network. Journal of Scientific Computing, 2018
  
• X. Shi, F. Park, L. Wang, J. Xin, and Y. Qi. Parallelization of a Color-Entropy Preprocessed Chan-Vese Model for Face Detection on Multi-core CPU and GPU. Parallel Computing, Vol 49, pp 28-49, 2015
  
  
• Qi, Y. and Bi, N., A multi-target approach for isolated word recognition using artificial neural network, Chinese Journal of Acoustics, 13, 160-168, 1994.
• Qi, Y. Hunt, B. and Bi, N. The use of fuzzy membership in network training for isolated word recognition. IEEE International Conference on Neural Networks, March, 1993.
• Qi, Y. and Hunt, B. Voiced-Unvoiced-Silence classifications of speech using hybrid features and a network classifier. IEEE Trans. on Speech and Audio Processing, 1, 250-255, 1993.
• Qi, Y. Application of a multilayer feedforward network to voiced-unvoiced-silence classifications of speech, Chinese Journal of Acoustics, 11, 167-178, 1992.
• Hunt, B., Qi, Y. , and Dekruger D., Fuzzy classification using set membership functions in the back propagation algorithm, Journal of Knowledge Engineering, 5, 62-74, 1992.

<RETURN>