Asymmetric Transfer Learning with Deep Gaussian Processes

By Melih Kandemir. 2015

52 citations recorded by the source corpus.

Subfields: Representation & Self-Supervised Learning, Probabilistic & Bayesian Methods

How researchers see this paper

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

In Representation & Self-Supervised Learning

1. Jian Shen
2. Yong Yu
3. Weinan Zhang
4. Yanru Qu
5. Melih Kandemir
6. Yew-Soon Ong
7. Jianfei Cai
8. Murat Sensoy

In Probabilistic & Bayesian Methods

1. Lance M. Kaplan
2. Jian Shen
3. Yong Yu
4. Weinan Zhang
5. Yanru Qu
6. Murat Sensoy
7. Melih Kandemir
8. Yew-Soon Ong

Citations in the corpus

• Evidential Deep Learning to Quantify Classification Uncertainty (2018, background): “Their power in prediction has been demonstrated in different contexts such as transfer learning [15] and deep learning [32].”
• Wasserstein Distance Guided Representation Learning for Domain Adaptation (2017, methodology): “…methods, which reweight/subsample the source samples to match the distribution of the target domain, thus training on the reweighted source samples guarantees classifiers with transferability (Huang et al. 2007; Chen, Weinberger, and Blitzer 2011; Chu, De la Torre, and Cohn 2013). ii).”
• Remarks on multi-output Gaussian process regression (2018, background): “The basic assumption is that the primary output has a few training points, but the secondary outputs, also denoted as source domains in transfer learning [24, 25, 26], usually have sufficient training points.”
• Not‐so‐supervised: A survey of semi‐supervised, multi‐instance, and transfer learning in medical image analysis (2018, background): “Kandemir and Hamprecht [2015] compare several classifiers on a dataset of Barrett’s cancer diagnosis in histopathology image, for which both bag-level and instancelevel labels are available. The best bag classifier is miGraph which is an exclusively bag-level method, while the best instance classifi”