已选(0)清除
条数/页: 排序方式: |
| MENet: A Memory-Based Network with Dual-Branch for Efficient Event Stream Processing 会议论文 , TELAVIV, 2022-6 作者: Linhui Sun; Yifan Zhang; Ke Cheng; Jian Cheng; Hanqing Lu Adobe PDF(1728Kb)  |  收藏  |  浏览/下载:87/20  |  提交时间:2024/01/22 Event-based model Dual-branch structure Memory bank |
| Multi-Granularity Pruning for Model Acceleration on Mobile Devices 会议论文 , 线上, 2022-07 作者: Zhao TL(赵天理); Zhang X(张希); Zhu WT(朱文涛); Wang JX(王家兴); Yang S(杨森); Liu J(刘季); Cheng J(程健) Adobe PDF(1919Kb)  |  收藏  |  浏览/下载:100/45  |  提交时间:2023/06/21 Deep Neural Networks Network Pruning Structured Pruning Non-structured Pruning Single Instruction Multiple Data |
| TinyNeRF: Towards 100 times Compression of Volume Radiance Fields 会议论文 , 线上, 2023-02 作者: Zhao TL(赵天理); Chen JY(陈嘉园); Leng C(冷聪); Cheng J(程健) Adobe PDF(2855Kb)  |  收藏  |  浏览/下载:169/37  |  提交时间:2023/06/21 Neural Radiance Fields Discrete Cosine Transformation Frequency Domain |
| Towards Automatic Model Compression via A Unified Two-Stage Framework 期刊论文 Pattern Recognition (PR), 2023, 卷号: 140, 页码: 109527 作者: Weihan Chen; Peisong Wang; Jian Cheng Adobe PDF(765Kb)  |  收藏  |  浏览/下载:107/33  |  提交时间:2023/06/20 Deep Neural Networks Model Compression Quantization Pruning |
| Towards Fully Sparse Training: Information Restoration with Spatial Similarity 会议论文 , Vancouver, British Columbia, Canada, 2022-04 作者: Xu WX(许伟翔); Wang PS(王培松); Cheng J(程健) Adobe PDF(556Kb)  |  收藏  |  浏览/下载:80/25  |  提交时间:2023/06/20 |
| Improving Extreme Low-bit Quantization with Soft Threshold 期刊论文 IEEE Transactions on Circuits and Systems for Video Technology, 2022, 页码: 1549 - 1563 作者: Xu WX(许伟翔); Wang PS(王培松); Cheng J(程健) Adobe PDF(2414Kb)  |  收藏  |  浏览/下载:75/26  |  提交时间:2023/06/20 |
| Towards Mixed-Precision Quantization of Neural Networks via Constrained Optimization 会议论文 , 线上举办, 2021-10-11 作者: Weihan Chen; Peisong Wang; Jian Cheng Adobe PDF(696Kb)  |  收藏  |  浏览/下载:113/35  |  提交时间:2023/06/20 |
| TBERT: Dynamic BERT Inference with Top-k Based Predictors 会议论文 , Antwerp, Belgium, 2023-4-17 作者: Liu, Zejian; Zhao, Kun; Cheng, Jian Adobe PDF(3426Kb)  |  收藏  |  浏览/下载:91/23  |  提交时间:2023/06/19 Transformer Dynamic Inference Pruning |
| Hardware Acceleration of Fully Quantized BERT for Efficient Natural Language Processing 会议论文 Proceedings of the 2021 Design, Automation and Test in Europe, DATE 2021, Virtual, Online, 2021-2 作者: Liu, Zejian; Li, Gang; Cheng, Jian Adobe PDF(593Kb)  |  收藏  |  浏览/下载:60/28  |  提交时间:2023/06/19 |
| Differentially Private Federated Learning with Local Regularization and Sparsification 会议论文 , 线上, 2022-6 作者: Cheng AD(程安达); Wang PS(王培松); Zhang X(张希); Cheng J(程健) Adobe PDF(312Kb)  |  收藏  |  浏览/下载:111/42  |  提交时间:2023/06/05 |