小米北京小米科技有限责任公司成立于2010年3月3日,是一家专注于智能硬件和电子产品研发的全球化移动互联网企业,同时也是一家专注于高端智能手机、互联网电视及智能家居生态链建设的创新型科技企业。 “为发烧而生”是小米的产品概念。“让每个人都能享受科技的乐趣”是小米公司的愿景。小米公司应用了互联网开发模式开发产品的模式,用极客精神做产品,用互联网模式干掉中间环节,致力让全球每个人,都能享用来自中国的优质科技产品。
arxiv, (2020)
By injecting unbiased Gaussian noise into skip connections’ output, we successfully let the optimization process be perceptible about the disturbed gradient flow
Cited by0BibtexViews160Links
1
0
Chu Xiangxiang, Li Xudong, Lu Yi,Zhang Bo, Li Jixiang
We propose a unified approach for one-shot neural architecture search, which bridges the gap between one-shot methodology and multi-path search space
Cited by0BibtexViews140Links
2
0
Chu Xiangxiang,Zhang Bo, Li Jixiang, Li Qingyuan, Xu Ruijun
We show that adding identity blocks introduces training instability
Cited by8BibtexViews91Links
0
0
Xiangxiang Chu,Bo Zhang, Ruijun Xu, Hailong Ma
arXiv: Neural and Evolutionary Computing, (2019)
We propose a multi-objective reinforced evolution algorithm in mobile neural architecture search, which seeks a better trade-off among various competing objectives
Cited by2BibtexViews96Links
0
0
Xiangxiang Chu,Bo Zhang, Hailong Ma, Ruijun Xu,Jixiang Li, Qingyuan Li
arXiv: Computer Vision and Pattern Recognition, (2019)
We presented a novel elastic method for NAS that incorporates both micro and macro search, dealing with neural architectures in multi-granularity
Cited by1BibtexViews134Links
0
0
ICASSP, pp.4042-4046, (2019)
Our total search cost has been substantially reduced to 12 GPU days
Cited by0BibtexViews86Links
0
0
Hailong Ma,Xiangxiang Chu,Bo Zhang, Shaohua Wan,Bo Zhang
arXiv: Computer Vision and Pattern Recognition, (2019)
The result confirms that MCANFAST has only a small loss of precision when compared to matrixed channel attention network, and it can still achieve better performance with fewer multi-adds and parameters than the state-of-the-art methods
Cited by0BibtexViews130Links
0
0
Li Jixiang, Liang Chuming,Zhang Bo, Wang Zhao, Xiang Fei,Chu Xiangxiang
We present a novel and efficient network for Acoustic Scene Classification tasks where its feature extractor is inspired by MobileNetV2
Cited by0BibtexViews120Links
0
0
Chu Xiangxiang,Zhang Bo, Xu Ruijun, Li Jixiang
We have thoroughly investigated the previously undiscussed fairness problem in weight-sharing neural architecture search approaches
Cited by0BibtexViews106Links
0
0
arXiv: Learning, (2018)
We introduce a new reinforcement learning algorithm called POP3D, which acts as a Trust Region Policy Optimization variant like PPO
Cited by2BibtexViews94Links
0
0