Results 111 to 120 of about 4,930,132 (374)

Self-supervised Character-to-Character Distillation for Text Recognition [PDF]

, 2022
Tongkun Guan, Wei Shen, Yang, Xue, Feng, Qi, Jiang, Zekun, Yang, Xiaokang   +5 more
openalex   +1 more source

Voltage‐Gated Dedoping of n‐Doped Poly(benzodifurandione) as an Interfacial Protective Mechanism in Electrochromic Devices

Advanced Functional Materials, EarlyView.
Electrochromic polymer stability under overpotential is improved by inserting an ultrathin, transparent n‐doped poly(benzodifurandione) interlayer between indium tin oxide and a poly(3,4‐propylenedioxythiophene)‐based electrochromic polymer. The interlayer supports rapid switching at operating bias, then becomes resistive near +0.8 V to suppress excess
Priyanka Rout, Palak Mehra, Won‐June Lee, Liyan You, Jianguo Mei   +4 more
wiley   +1 more source

Poster: Self-Supervised Quantization-Aware Knowledge Distillation [PDF]

, 2023
Kaiqi Zhao, Ming Zhao
openalex   +1 more source

Dynamic Corrective Self-Distillation for Better Fine-Tuning of Pretrained Models

, 2023
We tackle the challenging issue of aggressive fine-tuning encountered during the process of transfer learning of pre-trained language models (PLMs) with limited labeled downstream data.
Amara, Ibtihel, Chadha, Aman, Jain, Vinija   +2 more
core  

Establishing a Model Precursor System: Over a Decade of Research on Carbon Dots from the Citric Acid‐Urea System

Advanced Functional Materials, EarlyView.
The citric acid/urea (CA‐Urea) precursor system offers a versatile, scalable route to carbon dots with tunable luminescence and multifunctionality. Mechanistic insights into precursor chemistry and reaction parameters have enabled doping, surface modification, and hybridization strategies, yielding CDs for luminescent devices, sensing, catalysis ...
Yupeng Liu, Zhiqi Cai, Xiangxin Sun, Hanyi Zhang, Yiming Hao, Jun Wu, Zekun Yan, Xue Wu, Yiqi Liang, Liming Wang, Songnan Qu   +10 more
wiley   +1 more source

Improved Lane Detection Method Based on Convolutional Neural Network Using Self-attention Distillation [PDF]

, 2020
Xinyu Zhang, He Huang, Weiming Meng, Luo De'an   +3 more
openalex   +1 more source

Cascaded channel pruning using hierarchical self-distillation

Proceedings of the British Machine Vision Conference 2020, 2020
In this paper, we propose an approach for filter-level pruning with hierarchical knowledge distillation based on the teacher, teaching-assistant, and student framework. Our method makes use of teaching assistants at intermediate pruning levels that share the same architecture and weights as the target student.
Miles, Roy, Mikolajczyk, Krystian
openaire   +2 more sources

Optoelectronic Control of Redox Dynamics in POM Memristors for Noise‐Resilient Speech and Hardware‐Level Motion Recognition

Advanced Functional Materials, EarlyView.
Optoelectronic control of redox‐active polyoxometalate clusters in polymer matrices yields hybrid memristors with switchable volatile and non‐volatile modes, enabling reservoir‐type in‐sensor optical preprocessing and stable multilevel synapses for multimodal neuromorphic computing, including noise‐tolerant audiovisual keyword recognition and hardware ...
Xiangyu Ma, Ziyu Lv, Guohua Zhang, Zhongyue Xu, Yongbiao Zhai, Haiming Huang, Qiyan Zhang, Xiaojin Zhao, Yan Wang, Ye Zhou, Ziyu Xiong, Guanglong Ding, Wentao Xu, Su‐Ting Han   +13 more
wiley   +1 more source

Semantic Super-Resolution via Self-Distillation and Adversarial Learning

IEEE Access
Semantic super-resolution (SR) is an approach that improves the SR performance by leveraging semantic information about the scene. This study develops a novel semantic SR method that is based on the generative adversarial network (GAN) framework and self-
Hanhoon Park
doaj   +1 more source

On the Efficacy of Small Self-Supervised Contrastive Models without Distillation Signals [PDF]

, 2021
Haizhou Shi, Youcai Zhang, Siliang Tang, Wenjie Zhu, Yaqian Li, Yandong Guo, Yueting Zhuang   +6 more
openalex   +1 more source