A Label Propagation Strategy for CutMix in Multi-Label Remote Sensing Image Classification
Tom Burgert, Kai Norman Clasen, Jonas Klotz, Tim Siebert, Beg\"um Demir

TL;DR
This paper introduces a label propagation strategy to improve CutMix data augmentation for multi-label remote sensing image classification, effectively handling label noise and enhancing model performance.
Contribution
It proposes a novel label propagation method that leverages pixel-level class positional information to adapt CutMix for multi-label remote sensing tasks, reducing label noise issues.
Findings
Improves mAP macro by 2-4% over standard CutMix.
Demonstrates robustness with noisy class positional data.
Effective in both simulated and real scenarios.
Abstract
The development of supervised deep learning-based methods for multi-label scene classification (MLC) is one of the prominent research directions in remote sensing (RS). However, collecting annotations for large RS image archives is time-consuming and costly. To address this issue, several data augmentation methods have been introduced in RS. Among others, the CutMix data augmentation technique, which combines parts of two existing training images to generate an augmented image, stands out as a particularly effective approach. However, the direct application of CutMix in RS MLC can lead to the erasure or addition of class labels (i.e., label noise) in the augmented (i.e., combined) training image. To address this problem, we introduce a label propagation (LP) strategy that allows the effective application of CutMix in the context of MLC problems in RS without being affected by label…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsRemote Sensing and Land Use
MethodsCutMix
