Software

CHNR - Unsupervised Cross-Modal Hashing Method Robust to Noisy Training Image-Text Correspondences

RCML: Multi-Label Noise Robust Collaborative Learning

CCML: Consensual Collaborative Multi-Label Learning

Label Noise Injection Tools

Publications

Ahmet Kerem Aksoy, Mahdyar Ravanbakhsh, Begüm Demir, "Multi-Label Noise Robust Collaborative Learning for Remote Sensing Image Classification", IEEE Transactions on Neural Networks and Learning Systems, doi: 10.1109/TNNLS.2022.3209992, 2022.

Georgii Mikriukov, Mahdyar Ravanbakhsh, Begüm Demir, "An Unsupervised Cross-Modal Hashing Method Robust to Noisy Training Image-Text Correspondences in Remote Sensing", IEEE International Conference on Image Processing, 2022.

Ahmet Kerem Aksoy, Mahdyar Ravanbakhsh, Tristan Kreuziger, Begüm Demir, "A Consensual Collaborative Learning Method for Remote Sensing Image Classification Under Noisy Multi-Labels", IEEE International Conference on Image Processing, Alaska, USA, Sep. 2021.

Tom Burgert, Mahdyar Ravanbakhsh, Begüm Demir, "On the Effects of Different Types of Label Noise in Multi-Label Remote Sensing Image Classification", arXiv preprint arXiv:2207.13975, 2022.

Team

Our team at TU Berlin performs research in the fields of processing and analysis of remote sensing images for Earth observation with interdisciplinary approaches associated to remote sensing, machine learning, signal & image processing and big data management.

Contact Us