Xin Dong
Xin Dong
Verified email at - Homepage
Cited by
Cited by
Learning to Prune Deep Neural Networks via Layer-wise Optimal Brain Surgeon
X Dong, S Chen, SJ Pan
Advances in Neural Information Processing Systems 30 (NIPS 2017) pre-proceedings, 2017
Additive powers-of-two quantization: An efficient non-uniform discretization for neural networks
Y Li*, X Dong*, W Wang
International Conference on Learning Representations, 2019
Binary Ensemble Neural Network: More Bits per Network or More Networks per Bit?
S Zhu, X Dong, H Su
2019 Conference on Computer Vision and Pattern Recognition, 2019
exBERT: Extending pre-trained models with domain-specific vocabulary under constrained training resources
W Tai, HT Kung, X Dong, M Comiter, CF Kuo
Findings of the Association for Computational Linguistics: EMNLP 2020, 1433-1439, 2020
A free lunch from ANN: Towards efficient, accurate spiking neural networks calibration
Y Li, S Deng, X Dong, R Gong, S Gu
International Conference on Machine Learning, 6316-6325, 2021
Full-stack Optimization for Accelerating CNNs with FPGA Validation
B McDanel*, SQ Zhang*, HT Kung, X Dong
The 33rd ACM International Conference on Supercomputing, 2019
A Main/Subsidiary Network Framework for Simplifying Binary Neural Network
Y Xu*, X Dong*, Y Li, H Su
2019 Conference on Computer Vision and Pattern Recognition, 2019
Maestro: A memory-on-logic architecture for coordinated parallel use of many systolic arrays
HT Kung, B McDanel, SQ Zhang, X Dong, CC Chen
2019 IEEE 30th International Conference on Application-specific Systems …, 2019
RTN: Reparameterized ternary network
Y Li*, X Dong*, SQ Zhang, H Bai, Y Chen, W Wang
Proceedings of the AAAI Conference on Artificial Intelligence 34 (04), 4780-4787, 2020
Efficient bitwidth search for practical mixed precision neural network
Y Li, W Wang, H Bai, R Gong, X Dong, F Yu
arXiv preprint arXiv:2003.07577, 2020
Mixmix: All you need for data-free compression are feature and data mixing
Y Li, F Zhu, R Gong, M Shen, X Dong, F Yu, S Lu, S Gu
Proceedings of the IEEE/CVF International Conference on Computer Vision …, 2021
Training for multi-resolution inference using reusable quantization terms
SQ Zhang, B McDanel, HT Kung, X Dong
Proceedings of the 26th ACM International Conference on Architectural …, 2021
Dms: Differentiable dimension search for binary neural networks
Y Li, R Gong, F Yu, X Dong, X Liu
International Conference on Learning Representations, 2020
Neural Mean Discrepancy for Efficient Out-of-Distribution Detection
X Dong, J Guo, A Li, WT Ting, C Liu, HT Kung
Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022
Deep Neural Networks are Surprisingly Reversible: A Baseline for Zero-Shot Inversion
X Dong, H Yin, JM Alvarez, J Kautz, P Molchanov
arXiv preprint arXiv:2107.06304, 2021
SplitNets: Designing Neural Architectures for Efficient Distributed Computing on Head-Mounted Systems
X Dong, B De Salvo, M Li, C Liu, Z Qu, HT Kung, Z Li
Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022
Neural network training technique
H Yin, P Molchanov, JMA Lopez, X Dong
US Patent App. 17/195,451, 2022
SphereFed: Hyperspherical Federated Learning
X Dong, SQ Zhang, A Li, HT Kung
arXiv preprint arXiv:2207.09413, 2022
DRESS: Dynamic REal-time Sparse Subnets
Z Qu, SS Sarwar, X Dong, Y Li, E Sumbul, B De Salvo
arXiv preprint arXiv:2207.00670, 2022
Converting Artificial Neural Networks to Spiking Neural Networks via Parameter Calibration
Y Li, S Deng, X Dong, S Gu
arXiv preprint arXiv:2205.10121, 2022
The system can't perform the operation now. Try again later.
Articles 1–20