Hyperspectral Image Classification in the Presence of Noisy Labels

TL;DR

This paper introduces RLPA, a novel label cleansing algorithm for hyperspectral image classification that effectively mitigates the impact of noisy labels by leveraging spectral-spatial information and label propagation techniques.

Contribution

The paper proposes a random label propagation algorithm (RLPA) that uses spectral-spatial constraints to reduce label noise in hyperspectral image classification, improving accuracy.

Findings

RLPA significantly improves classification accuracy over four major classifiers.

The method effectively reduces the impact of noisy labels in hyperspectral data.

Experimental results show notable gains in OA, AA, and Kappa metrics.

Abstract

Label information plays an important role in supervised hyperspectral image classification problem. However, current classification methods all ignore an important and inevitable problem---labels may be corrupted and collecting clean labels for training samples is difficult, and often impractical. Therefore, how to learn from the database with noisy labels is a problem of great practical importance. In this paper, we study the influence of label noise on hyperspectral image classification, and develop a random label propagation algorithm (RLPA) to cleanse the label noise. The key idea of RLPA is to exploit knowledge (e.g., the superpixel based spectral-spatial constraints) from the observed hyperspectral images and apply it to the process of label propagation. Specifically, RLPA first constructs a spectral-spatial probability transfer matrix (SSPTM) that simultaneously considers the spectral similarity and superpixel based spatial information. It then randomly chooses some training samples as "clean" samples and sets the rest as unlabeled samples, and propagates the label information from the "clean" samples to the rest unlabeled samples with the SSPTM. By repeating the random assignment (of "clean" labeled samples and unlabeled samples) and propagation, we can obtain multiple labels for each training sample. Therefore, the final propagated label can be calculated by a majority vote algorithm. Experimental studies show that RLPA can reduce the level of noisy label and demonstrates the advantages of our proposed method over four major classifiers with a significant margin---the gains in terms of the average OA, AA, Kappa are impressive, e.g., 9.18%, 9.58%, and 0.1043. The Matlab source code is available at https://github.com/junjun-jiang/RLPA