Training deep neural-networks based on unreliable labels

By Alan Joseph Bekker, Jacob Goldberger. 2016

157 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Learning and Refining of Privileged Information-Based RNNs for Action Recognition from Depth Sequences (2017, methodology): “Apart from optimizing network parameters, the bridging matrix of modeling latent PI can be updated iteratively by a closed-form solution in the M-step of EM procedure [31, 36, 3]:”
Image Classification with Deep Learning in the Presence of Noisy Labels: A Survey (2019, methodology): “Iterative calculation: EM [48, 49, 27], fully connected layer [50], anchor point estimate [51] Drichlet-distribution [52] c.”
Decoupling "when to update" from "how to update" (2017, background): “It is worth noting that there are some other works that suggest methods that are very similar to [36, 15], with a slightly different objective or training method [5, 20], or otherwise suggest a complicated process which involves estimation of the classdependent noise probabilities [32].”
Deep learning with noisy labels: exploring techniques and remedies in medical image analysis (2019, methodology): “[130] used a combination of EM and error back-propagation for end-to-end training with a noise layer.”
Unbox the black-box for the medical explainable AI via multi-modal and multi-centre data fusion: A mini-review, two showcases and beyond (2021, unknown): “Inspired by [167], we model the noise transaction distribution 𝑃 ( 𝑧 𝑐 = 𝑖 | 𝑦 𝑐 = 𝑗,  ) , which transforms the true posterior distribution 𝑃 ( 𝑦 𝑐 |  ) to the noisy label distribution 𝑃 ( 𝑧 𝑐 |  ) by In practice, we estimate the noise transaction distribution where 𝑖,𝑗 ∈ {0 , 1}…”
Training deep neural-networks using a noise adaptation layer (2016, methodology): “Several variations of this paradigm have been proposed (e.g. Minh & Hinton (2012), Bekker & Goldberger (2016)).”