Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox
Picture for Xinshao Wang

Xinshao Wang

Not All Knowledge Is Created Equal


Jun 02, 2021
Ziyun Li, Xinshao Wang, Haojin Yang, Di Hu, Neil M. Robertson, David A. Clifton, Christoph Meinel

Figure 1 for Not All Knowledge Is Created Equal
Figure 2 for Not All Knowledge Is Created Equal
Figure 3 for Not All Knowledge Is Created Equal
Figure 4 for Not All Knowledge Is Created Equal
* Selective mutual knowledge distillation 
  Access Paper or Ask Questions

ProSelfLC: Progressive Self Label Correction for Training Robust Deep Neural Networks


Jun 08, 2020
Xinshao Wang, Yang Hua, Elyor Kodirov, Neil M. Robertson

Figure 1 for ProSelfLC: Progressive Self Label Correction for Training Robust Deep Neural Networks
Figure 2 for ProSelfLC: Progressive Self Label Correction for Training Robust Deep Neural Networks
Figure 3 for ProSelfLC: Progressive Self Label Correction for Training Robust Deep Neural Networks
Figure 4 for ProSelfLC: Progressive Self Label Correction for Training Robust Deep Neural Networks
* Open discussion: we show it's fine for a learner (student) to be confident towards a correct low entropy status. Then more research attention should be paid to the definition of correct knowledge, as in genera we accept, human annotations used for learning supervision may be biased, subjective, and wrong 
  Access Paper or Ask Questions

ProSelfLC: Progressive Self Label Correction for Target Revising in Label Noise


May 17, 2020
Xinshao Wang, Yang Hua, Elyor Kodirov, Neil M. Robertson

Figure 1 for ProSelfLC: Progressive Self Label Correction for Target Revising in Label Noise
Figure 2 for ProSelfLC: Progressive Self Label Correction for Target Revising in Label Noise
Figure 3 for ProSelfLC: Progressive Self Label Correction for Target Revising in Label Noise
Figure 4 for ProSelfLC: Progressive Self Label Correction for Target Revising in Label Noise
* Learning target revising, softer targets, entropy regularisation, EM algorithm. A target label distribution should define both the semantic class and similarity structure! 
  Access Paper or Ask Questions

Instance Cross Entropy for Deep Metric Learning


Nov 22, 2019
Xinshao Wang, Elyor Kodirov, Yang Hua, Neil Robertson

Figure 1 for Instance Cross Entropy for Deep Metric Learning
Figure 2 for Instance Cross Entropy for Deep Metric Learning
Figure 3 for Instance Cross Entropy for Deep Metric Learning
Figure 4 for Instance Cross Entropy for Deep Metric Learning

  Access Paper or Ask Questions

ID-aware Quality for Set-based Person Re-identification


Nov 20, 2019
Xinshao Wang, Elyor Kodirov, Yang Hua, Neil M. Robertson

Figure 1 for ID-aware Quality for Set-based Person Re-identification
Figure 2 for ID-aware Quality for Set-based Person Re-identification
Figure 3 for ID-aware Quality for Set-based Person Re-identification
Figure 4 for ID-aware Quality for Set-based Person Re-identification
* A Set-based Person Re-identification Baseline: Simple Average Fusion of Global Spatial Representations, without temporal information, without parts/poses/attributes information 
  Access Paper or Ask Questions

Emphasis Regularisation by Gradient Rescaling for Training Deep Neural Networks with Noisy Labels


May 27, 2019
Xinshao Wang, Yang Hua, Elyor Kodirov, Neil Robertson

Figure 1 for Emphasis Regularisation by Gradient Rescaling for Training Deep Neural Networks with Noisy Labels
Figure 2 for Emphasis Regularisation by Gradient Rescaling for Training Deep Neural Networks with Noisy Labels
Figure 3 for Emphasis Regularisation by Gradient Rescaling for Training Deep Neural Networks with Noisy Labels
Figure 4 for Emphasis Regularisation by Gradient Rescaling for Training Deep Neural Networks with Noisy Labels
* Question: What training examples should be focused and how much more should they be emphasised when training DNNs under label noise? Answer: When noise rate is higher, we can improve a model's robustness by focusing on relatively less difficult examples 
  Access Paper or Ask Questions

Improving MAE against CCE under Label Noise


Apr 19, 2019
Xinshao Wang, Elyor Kodirov, Yang Hua, Neil M. Robertson

Figure 1 for Improving MAE against CCE under Label Noise
Figure 2 for Improving MAE against CCE under Label Noise
Figure 3 for Improving MAE against CCE under Label Noise
Figure 4 for Improving MAE against CCE under Label Noise
* Mean Absolute Error, Cross Entropy, Data fitting(Overfitting, Underfitting), Noise Robustness, Label Noise 
  Access Paper or Ask Questions

Ranked List Loss for Deep Metric Learning


Apr 16, 2019
Xinshao Wang, Yang Hua, Elyor Kodirov, Guosheng Hu, Romain Garnier, Neil M. Robertson

Figure 1 for Ranked List Loss for Deep Metric Learning
Figure 2 for Ranked List Loss for Deep Metric Learning
Figure 3 for Ranked List Loss for Deep Metric Learning
Figure 4 for Ranked List Loss for Deep Metric Learning
* CVPR19, Deep Metric Learning/Feature Embedding, Learning Representations, Image Retrieval/Clustering 
  Access Paper or Ask Questions

Deep Metric Learning by Online Soft Mining and Class-Aware Attention


Nov 04, 2018
Xinshao Wang, Yang Hua, Elyor Kodirov, Guosheng Hu, Neil M. Robertson

Figure 1 for Deep Metric Learning by Online Soft Mining and Class-Aware Attention
Figure 2 for Deep Metric Learning by Online Soft Mining and Class-Aware Attention
Figure 3 for Deep Metric Learning by Online Soft Mining and Class-Aware Attention
Figure 4 for Deep Metric Learning by Online Soft Mining and Class-Aware Attention
* Deep Metric Learning, Person Re-identification (AAAI 2019) 
  Access Paper or Ask Questions