# A deep multiple instance learning approach based on coarse labels for high-resolution land-cover mapping

arXiv: https://arxiv.org/abs/2510.06769 · HTML: https://mlsanity.com/paper/2510.06769/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 20 references that are in the map.
- First posted on arXiv 8 Oct 2025.

## Builds on (most cited first, 10 of 10)

- [Attention-based Deep Multiple Instance Learning](https://mlsanity.com/paper/1802.04712/) (2018)
- [Positive-Unlabeled Learning with Non-Negative Risk Estimator](https://mlsanity.com/paper/1703.00593/) (2017)
- [Revisiting Multiple Instance Neural Networks](https://mlsanity.com/paper/1610.02501/) (2016)
- [SEN12MS -- A Curated Dataset of Georeferenced Multi-Spectral Sentinel-1/2 Imagery for Deep Learning and Data Fusion](https://mlsanity.com/paper/1906.07789/) (2019)
- [Theoretical Comparisons of Positive-Unlabeled Learning against Positive-Negative Learning](https://mlsanity.com/paper/1603.03130/) (2016)
- [A Comprehensive Analysis of Weakly-Supervised Semantic Segmentation in Different Image Domains](https://mlsanity.com/paper/1912.11186/) (2019)
- [A Survey on Deep Learning with Noisy Labels: How to train your model when you cannot trust on the annotations?](https://mlsanity.com/paper/2012.03061/) (2020)
- [Weakly Supervised Semantic Segmentation of Satellite Images](https://mlsanity.com/paper/1904.03983/) (2019)
- [Weakly Supervised Semantic Segmentation of Remote Sensing Images for Tree Species Classification Based on Explanation Methods](https://mlsanity.com/paper/2201.07495/) (2022)
- [A Novel Technique for Robust Training of Deep Networks With Multisource Weak Labeled Remote Sensing Data](https://mlsanity.com/paper/2510.05760/) (2025)

## Abstract (arXiv)

The quantity and the quality of the training labels are central problems in high-resolution land-cover mapping with machine-learning-based solutions. In this context, weak labels can be gathered in large quantities by leveraging on existing low-resolution or obsolete products. In this paper, we address the problem of training land-cover classifiers using high-resolution imagery (e.g., Sentinel-2) and weak low-resolution reference data (e.g., MODIS -derived land-cover maps). Inspired by recent works in Deep Multiple Instance Learning (DMIL), we propose a method that trains pixel-level multi-class classifiers and predicts low-resolution labels (i.e., patch-level classification), where the actual high-resolution labels are learned implicitly without direct supervision. This is achieved with flexible pooling layers that are able to link the semantics of the pixels in the high-resolution imagery to the low-resolution reference labels. Then, the Multiple Instance Learning (MIL) problem is re-framed in a multi-class and in a multi-label setting. In the former, the low-resolution annotation represents the majority of the pixels in the patch. In the latter, the annotation only provides us information on the presence of one of the land-cover classes in the patch and thus multiple labels can be considered valid for a patch at a time, whereas the low-resolution labels provide us only one label. Therefore, the classifier is trained with a Positive-Unlabeled Learning (PUL) strategy. Experimental results on the 2020 IEEE GRSS Data Fusion Contest dataset show the effectiveness of the proposed framework compared to standard training strategies.