DatUS^2: Data-driven Unsupervised Semantic Segmentation with Pre-trained Self-supervised Vision Transformer

1 code implementation • 23 Jan 2024 • Sonal Kumar, Arijit Sur, Rashmi Dutta Baruah

Also, the best version of DatUS^2 outperforms the existing state-of-the-art method for the unsupervised dense semantic segmentation task with 15. 02% MiOU and 21. 47% Pixel accuracy on the SUIM dataset.

Segmentation Unsupervised Semantic Segmentation

Explicit Context Integrated Recurrent Neural Network for Sensor Data Applications

no code implementations • 12 Jan 2023 • Rashmi Dutta Baruah, Mario Muñoz Organero

The additional data that are available from the problem domain, which cannot be used independently for learning models, constitute context.