Zobrazeno 1 - 10
of 148
pro vyhledávání: '"Robertson, Neil M."'
Autor:
Wang, Xinshao, Hua, Yang, Kodirov, Elyor, Mukherjee, Sankha Subhra, Clifton, David A., Robertson, Neil M.
There is a family of label modification approaches including self and non-self label correction (LC), and output regularisation. They are widely used for training robust deep neural networks (DNNs), but have not been mathematically and thoroughly ana
Externí odkaz:
http://arxiv.org/abs/2207.00118
Autor:
Li, Ziyun, Wang, Xinshao, Hu, Di, Robertson, Neil M., Clifton, David A., Meinel, Christoph, Yang, Haojin
Mutual knowledge distillation (MKD) improves a model by distilling knowledge from another model. However, \textit{not all knowledge is certain and correct}, especially under adverse conditions. For example, label noise usually leads to less reliable
Externí odkaz:
http://arxiv.org/abs/2106.01489
Autor:
Sixta, Tomáš, Junior, Julio C. S. Jacques, Buch-Cardona, Pau, Robertson, Neil M., Vazquez, Eduard, Escalera, Sergio
This work summarizes the 2020 ChaLearn Looking at People Fair Face Recognition and Analysis Challenge and provides a description of the top-winning solutions and analysis of the results. The aim of the challenge was to evaluate accuracy and bias in g
Externí odkaz:
http://arxiv.org/abs/2009.07838
Autor:
Larabi, Slimane, Robertson, Neil M.
In this paper we deal with contour detection based on the recent image analogy principle which has been successfully used for super-resolution, texture and curves synthesis and interactive editing. Hand-drawn outlines are initially as benchmarks. Giv
Externí odkaz:
http://arxiv.org/abs/2007.11047
Recently, several approaches have been proposed to solve language generation problems. Transformer is currently state-of-the-art seq-to-seq model in language generation. Reinforcement Learning (RL) is useful in solving exposure bias and the optimisat
Externí odkaz:
http://arxiv.org/abs/2006.11714
Publikováno v:
CVPR 2021
To train robust deep neural networks (DNNs), we systematically study several target modification approaches, which include output regularisation, self and non-self label correction (LC). Two key issues are discovered: (1) Self LC is the most appealin
Externí odkaz:
http://arxiv.org/abs/2005.03788
Autor:
Li, Yonggang, Hu, Guosheng, Wang, Yongtao, Hospedales, Timothy, Robertson, Neil M., Yang, Yongxin
Data augmentation (DA) techniques aim to increase data variability, and thus train deep networks with better generalisation. The pioneering AutoAugment automated the search for optimal DA policies with reinforcement learning. However, AutoAugment is
Externí odkaz:
http://arxiv.org/abs/2003.03780
Set-based person re-identification (SReID) is a matching problem that aims to verify whether two sets are of the same identity (ID). Existing SReID models typically generate a feature representation per image and aggregate them to represent the set a
Externí odkaz:
http://arxiv.org/abs/1911.09143
Real-world large-scale datasets usually contain noisy labels and are imbalanced. Therefore, we propose derivative manipulation (DM), a novel and general example weighting approach for training robust deep models under these adverse conditions. DM has
Externí odkaz:
http://arxiv.org/abs/1905.11233
In this work, we study robust deep learning against abnormal training data from the perspective of example weighting built in empirical loss functions, i.e., gradient magnitude with respect to logits, an angle that is not thoroughly studied so far. C
Externí odkaz:
http://arxiv.org/abs/1903.12141