Xin Dong

发表

Field-Conﬁgurable Multi-resolution Inference: Rethinking Quantization

H. T. Kung, S. Zhang, Bradley McDanel, 2020 .

SphereFed: Hyperspherical Federated Learning

Ang Li, S. Zhang, Xin Dong, 2022, ECCV.

Neural Mean Discrepancy for Efficient Out-of-Distribution Detection

Ang Li, Junfeng Guo, Cong Liu, 2021, 2104.11408.

DRESS: Dynamic REal-time Sparse Subnets

Syed Shakib Sarwar, H. Sumbul, B. D. Salvo, 2022, ArXiv.

Converting Artificial Neural Networks to Spiking Neural Networks via Parameter Calibration

Xin Dong, Yuhang Li, Shi-Wee Deng, 2022, ArXiv.

Additive Powers-of-Two Quantization: An Efficient Non-uniform Discretization for Neural Networks

Wei Wang, Xin Dong, Yuhang Li, 2019, International Conference on Learning Representations.

Binary Ensemble Neural Network: More Bits per Network or More Networks per Bit?

Xin Dong, Shilin Zhu, Hao Su, 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

Supplementary Materials for AQD: Towards Accurate Quantized Object Detection

Steven K. Esser, Andrew G. Howard, Dmitry Kalenichenko, 2021 .

RTN: Reparameterized Ternary Network pdf

Wei Wang, Yuhang Li, Sai Qian Zhang, 2019, AAAI.

Deep Neural Networks are Surprisingly Reversible: A Baseline for Zero-Shot Inversion pdf

Pavlo Molchanov, Jan Kautz, Jose M. Alvarez, 2021, ArXiv.

MixMix: All You Need for Data-Free Compression Are Feature and Data Mixing

F. Yu, Xin Dong, Shaoqing Lu, 2020, 2021 IEEE/CVF International Conference on Computer Vision (ICCV).

A Free Lunch From ANN: Towards Efficient, Accurate Spiking Neural Networks Calibration pdf

Ruihao Gong, Yuhang Li, Shikuang Deng, 2021, ICML.

Neural Mean Discrepancy for Efficient Out-of-Distribution Detection

Ang Li, Junfeng Guo, Cong Liu, 2021, 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

Full-stack optimization for accelerating CNNs using powers-of-two weights with FPGA validation

H. T. Kung, Sai Qian Zhang, Bradley McDanel, 2019, ICS.

Additive Powers-of-Two Quantization: A Non-uniform Discretization for Neural Networks pdf

Yuhang Li, Wei Wang, Xin Dong, 2019, ICLR 2020.

Full-stack Optimization for Accelerating CNNs with FPGA Validation pdf

H. T. Kung, Sai Qian Zhang, Bradley McDanel, 2019, ArXiv.

exBERT: Extending Pre-trained Models with Domain-specific Vocabulary Under Constrained Training Resources

H. T. Kung, Xin Dong, Wen Tai, 2020, FINDINGS.

Additive Powers-of-Two Quantization: A Non-uniform Discretization for Neural Networks

Wei Wang, Xin Dong, Yuhang Li, 2019, ICLR 2020.

A Main/Subsidiary Network Framework for Simplifying Binary Neural Networks

Xin Dong, Hao Su, Yudian Li, 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

Maestro: A Memory-on-Logic Architecture for Coordinated Parallel Use of Many Systolic Arrays

H. T. Kung, Sai Qian Zhang, Bradley McDanel, 2019, 2019 IEEE 30th International Conference on Application-specific Systems, Architectures and Processors (ASAP).

Efficient Bitwidth Search for Practical Mixed Precision Neural Network pdf

Yuhang Li, Ruihao Gong, Fengwei Yu, 2020, ArXiv.

ABSent: Cross-Lingual Sentence Representation Mapping with Bidirectional GANs

Gerard de Melo, Xin Dong, Yuting Wang, 2020, AAAI.

SplitNets: Designing Neural Architectures for Efficient Distributed Computing on Head-Mounted Systems

Meng Li, B. D. Salvo, Zhongnan Qu, 2022, 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

Training for multi-resolution inference using reusable quantization terms

Sai Qian Zhang, Bradley McDanel, H. T. Kung, 2021, ASPLOS.