Class Prior-Free Positive-Unlabeled Learning with Taylor Variational Loss for Hyperspectral Remote Sensing Imagery

08/29/2023

∙

Positive-unlabeled learning (PU learning) in hyperspectral remote sensing imagery (HSI) is aimed at learning a binary classifier from positive and unlabeled data, which has broad prospects in various earth vision applications. However, when PU learning meets limited labeled HSI, the unlabeled data may dominate the optimization process, which makes the neural networks overfit the unlabeled data. In this paper, a Taylor variational loss is proposed for HSI PU learning, which reduces the weight of the gradient of the unlabeled data by Taylor series expansion to enable the network to find a balance between overfitting and underfitting. In addition, the self-calibrated optimization strategy is designed to stabilize the training process. Experiments on 7 benchmark datasets (21 tasks in total) validate the effectiveness of the proposed method. Code is at: https://github.com/Hengwei-Zhao96/T-HOneCls.

READ FULL TEXT

Class Prior-Free Positive-Unlabeled Learning with Taylor Variational Loss for Hyperspectral Remote Sensing Imagery

Evaluating Self and Semi-Supervised Methods for Remote Sensing Segmentation Tasks

Alternate Estimation of a Classifier and the Class-Prior from Positive and Unlabeled Data

Dist-PU: Positive-Unlabeled Learning from a Label Distribution Perspective

Learning Classifiers on Positive and Unlabeled Data with Policy Gradient

Bringing Giant Neural Networks Down to Earth with Unlabeled Data

Scalable Evaluation and Improvement of Document Set Expansion via Neural Positive-Unlabeled Learning

Learning One-Class Hyperspectral Classifier from Positive and Unlabeled Data for Low Proportion Target

Class Prior-Free Positive-Unlabeled Learning with Taylor Variational Loss for Hyperspectral Remote Sensing Imagery

Related Research

Evaluating Self and Semi-Supervised Methods for Remote Sensing Segmentation Tasks

Alternate Estimation of a Classifier and the Class-Prior from Positive and Unlabeled Data

Dist-PU: Positive-Unlabeled Learning from a Label Distribution Perspective

Learning Classifiers on Positive and Unlabeled Data with Policy Gradient

Bringing Giant Neural Networks Down to Earth with Unlabeled Data

Scalable Evaluation and Improvement of Document Set Expansion via Neural Positive-Unlabeled Learning

Learning One-Class Hyperspectral Classifier from Positive and Unlabeled Data for Low Proportion Target