Epoch-evolving Gaussian Process Guided Learning

06/25/2020
by   Jiabao Cui, et al.
0

In this paper, we propose a novel learning scheme called epoch-evolving Gaussian Process Guided Learning (GPGL), which aims at characterizing the correlation information between the batch-level distribution and the global data distribution. Such correlation information is encoded as context labels and needs renewal every epoch. With the guidance of the context label and ground truth label, GPGL scheme provides a more efficient optimization through updating the model parameters with a triangle consistency loss. Furthermore, our GPGL scheme can be further generalized and naturally applied to the current deep models, outperforming the existing batch-based state-of-the-art models on mainstream datasets (CIFAR-10, CIFAR-100, and Tiny-ImageNet) remarkably.

READ FULL TEXT

page 3

page 5

research
10/22/2016

Multitask Learning of Vegetation Biochemistry from Hyperspectral Data

Statistical models have been successful in accurately estimating the bio...
research
03/03/2022

Debiased Batch Normalization via Gaussian Process for Generalizable Person Re-Identification

Generalizable person re-identification aims to learn a model with only s...
research
10/31/2019

Confident Learning: Estimating Uncertainty in Dataset Labels

Learning exists in the context of data, yet notions of confidence typica...
research
08/15/2019

Adaptive Regularization of Labels

Recently, a variety of regularization techniques have been widely applie...
research
12/02/2020

Regularization via Adaptive Pairwise Label Smoothing

Label Smoothing (LS) is an effective regularizer to improve the generali...
research
10/06/2022

Leveraging Instance Features for Label Aggregation in Programmatic Weak Supervision

Programmatic Weak Supervision (PWS) has emerged as a widespread paradigm...

Please sign up or login with your details

Forgot password? Click here to reset