no code implementations • 23 Dec 2022 • Yuqiao Liu, Haipeng Li, Yanan sun, Shuaicheng Liu
NAS without training (WOT) score is such a metric, which estimates the final trained accuracy of the architecture through the ability to distinguish different inputs in the activation layer.
2 code implementations • NeurIPS 2022 • Yuqiao Liu, Yehui Tang ~Yehui_Tang1, Zeqiong Lv, Yunhe Wang, Yanan sun
To solve this issue, we propose a Cross-Domain Predictor (CDP), which is trained based on the existing NAS benchmark datasets (e. g., NAS-Bench-101), but can be used to find high-performance architectures in large-scale search spaces.
no code implementations • 3 Jul 2022 • Xiangning Xie, Yuqiao Liu, Yanan sun, Mengjie Zhang, Kay Chen Tan
Performance predictors can greatly alleviate the prohibitive cost of NAS by directly predicting the performance of DNNs.
no code implementations • 15 Nov 2021 • Yuhan Fang, Yuqiao Liu, Yanan sun
As a consequence, it requires the designers to develop expertise in both CF and DNNs, which limits the application of deep learning methods in CF and the accuracy of recommended results.
1 code implementation • 9 Aug 2021 • Xiangning Xie, Yuqiao Liu, Yanan sun, Gary G. Yen, Bing Xue, Mengjie Zhang
The paper conducts efficient comparison experiments on eight ENAS algorithms with high GPU utilization on this platform.
1 code implementation • ICCV 2021 • Yuqiao Liu, Yehui Tang, Yanan sun
Specifically, a homogeneous architecture augmentation algorithm is proposed in HAAP to generate sufficient training data taking the use of homogeneous representation.
no code implementations • 25 Oct 2020 • Yuqiao Liu, Yudan Wang, Ying Zhao, Zhixiang Li
Transgender community is experiencing a huge disparity in mental health conditions compared with the general population.
no code implementations • 25 Aug 2020 • Yuqiao Liu, Yanan sun, Bing Xue, Mengjie Zhang, Gary G. Yen, Kay Chen Tan
Deep Neural Networks (DNNs) have achieved great success in many applications.
no code implementations • 15 Aug 2020 • Yuqiao Liu, Yanan sun, Bing Xue, Mengjie Zhang
Hyperspectral images (HSIs) are susceptible to various noise factors leading to the loss of information, and the noise restricts the subsequent HSIs object detection and classification tasks.