Learning from noisy labels with deep neural networks: A survey
Deep learning has achieved remarkable success in numerous domains with help from large
amounts of big data. However, the quality of data labels is a concern because of the lack of …
amounts of big data. However, the quality of data labels is a concern because of the lack of …
Recent advances in optimal transport for machine learning
Recently, Optimal Transport has been proposed as a probabilistic framework in Machine
Learning for comparing and manipulating probability distributions. This is rooted in its rich …
Learning for comparing and manipulating probability distributions. This is rooted in its rich …
Open-set label noise can improve robustness against inherent label noise
H Wei, L Tao, R ** the model prediction
In the presence of noisy labels, designing robust loss functions is critical for securing the
generalization performance of deep neural networks. Cross Entropy (CE) loss has been …
generalization performance of deep neural networks. Cross Entropy (CE) loss has been …
Ot-filter: An optimal transport filter for learning with noisy labels
C Feng, Y Ren, X **e - … of the IEEE/CVF Conference on …, 2023 - openaccess.thecvf.com
The success of deep learning is largely attributed to the training over clean data. However,
data is often coupled with noisy labels in practice. Learning with noisy labels is challenging …
data is often coupled with noisy labels in practice. Learning with noisy labels is challenging …
Two-stream graph convolutional network-incorporated latent feature analysis
F Bi, T He, Y **e, X Luo - IEEE Transactions on Services …, 2023 - ieeexplore.ieee.org
Historical Quality-of-Service (QoS) data describing existing user-service invocations are vital
to understanding user behaviors and cloud service conditions. Collaborative Filtering (CF) …
to understanding user behaviors and cloud service conditions. Collaborative Filtering (CF) …
Learning to rectify for robust learning with noisy labels
Label noise significantly degrades the generalization ability of deep models in applications.
Effective strategies and approaches (eg, re-weighting or loss correction) are designed to …
Effective strategies and approaches (eg, re-weighting or loss correction) are designed to …
Transferring annotator-and instance-dependent transition matrix for learning from crowds
Learning from crowds describes that the annotations of training data are obtained with
crowd-sourcing services. Multiple annotators each complete their own small part of the …
crowd-sourcing services. Multiple annotators each complete their own small part of the …
Efficient data-driven crop pest identification based on edge distance-entropy for sustainable agriculture
Human agricultural activities are always accompanied by pests and diseases, which have
brought great losses to the production of crops. Intelligent algorithms based on deep …
brought great losses to the production of crops. Intelligent algorithms based on deep …