no code implementations • 14 Jan 2024 • Guangyu Meng, Ruyu Zhou, Liu Liu, Peixian Liang, Fang Liu, Danny Chen, Michael Niemier, X. Sharon Hu
Earth Mover's Distance (EMD) is an important similarity measure between two distributions, used in computer vision and many other application domains.
no code implementations • 4 Sep 2022 • Suraj Mishra, Yizhe Zhang, Li Zhang, Tianyu Zhang, X. Sharon Hu, Danny Z. Chen
Specifically, we analyze the convolutional network's behavior (field-of-view) to find the location of deep supervision for improved feature extraction.
no code implementations • 16 Jul 2022 • Mengyuan Li, Arman Kazemi, Ann Franchesca Laguna, X. Sharon Hu
AMPER replaces the widely-used time-costly tree-traversal-based priority sampling in PER while preserving the learning performance.
no code implementations • IEEE Transactions on Medical Imaging 2022 • Suraj Mishra, Yizhe Zhang, Danny Z. Chen, X. Sharon Hu
In this paper, we study medical image segmentation by focusing on robust data-specific feature extraction to achieve improved dense prediction.
no code implementations • 15 Apr 2022 • Ruibin Mao, Bo Wen, Yahui Zhao, Arman Kazemi, Ann Franchesca Laguna, Michael Neimier, X. Sharon Hu, Xia Sheng, Catherine E. Graves, John Paul Strachan, Can Li
Memory augmented neural network has been proposed to achieve the goal, but the memory module has to be stored in an off-chip memory due to its size.
no code implementations • 6 Jul 2021 • Suraj Mishra, Danny Z. Chen, X. Sharon Hu
Finally, the mapping is used to determine the convolutional layer-wise multiplicative factor for generating a compressed network.
no code implementations • 17 Apr 2021 • Suraj Mishra, Danny Z. Chen, X. Sharon Hu
In this paper, we study retinal vessel segmentation by incorporating tiny vessel segmentation into our framework for the overall accurate vessel segmentation.
no code implementations • 13 Nov 2020 • Arman Kazemi, Mohammad Mehdi Sharifi, Ann Franchesca Laguna, Franz Müller, Ramin Rajaei, Ricardo Olivo, Thomas Kämpfe, Michael Niemier, X. Sharon Hu
Moreover, this approach achieves accuracies comparable to floating-point precision implementations in software for NN classification and one/few-shot learning tasks.
no code implementations • 29 May 2019 • Andrew W. Stephan, Qiuwen Lou, Michael Niemier, X. Sharon Hu, Steven J. Koester
A new spintronic nonvolatile memory cell analogous to 1T DRAM with non-destructive read is proposed.
no code implementations • 28 Feb 2019 • Qiuwen Lou, Indranil Palit, Tang Li, Andras Horvath, Michael Niemier, X. Sharon Hu
While it is well-known that CeNNs can be well-suited for spatio-temporal information processing, few (if any) studies have quantified the energy/delay/accuracy of a CeNN-friendly algorithm and compared the CeNN-based approach to the best von Neumann algorithm at the application level.
1 code implementation • 6 Jan 2019 • Suraj Mishra, Peixian Liang, Adam Czajka, Danny Z. Chen, X. Sharon Hu
Convolutional neural networks (CNNs) for biomedical image analysis are often of very large size, resulting in high memory requirement and high latency of operations.
no code implementations • 30 Oct 2018 • Qiuwen Lou, Chenyun Pan, John McGuiness, Andras Horvath, Azad Naeemi, Michael Niemier, X. Sharon Hu
Deep neural network (DNN) accelerators with improved energy and delay are desirable for meeting the requirements of hardware targeted for IoT and edge computing systems.
no code implementations • 1 Sep 2018 • Xiaowei Xu, Xinyi Zhang, Bei Yu, X. Sharon Hu, Christopher Rowen, Jingtong Hu, Yiyu Shi
The 55th Design Automation Conference (DAC) held its first System Design Contest (SDC) in 2018.