DeepAI AI Chat
Log In Sign Up

Epoch-evolving Gaussian Process Guided Learning

by   Jiabao Cui, et al.
Zhejiang University

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.


page 3

page 5


Multitask Learning of Vegetation Biochemistry from Hyperspectral Data

Statistical models have been successful in accurately estimating the bio...

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

Generalizable person re-identification aims to learn a model with only s...

Confident Learning: Estimating Uncertainty in Dataset Labels

Learning exists in the context of data, yet notions of confidence typica...

Adaptive Regularization of Labels

Recently, a variety of regularization techniques have been widely applie...

Regularization via Adaptive Pairwise Label Smoothing

Label Smoothing (LS) is an effective regularizer to improve the generali...

Leveraging Instance Features for Label Aggregation in Programmatic Weak Supervision

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