PPOT and SPPOT

About PPOT

rhfeiyang/PPOT

Official implementation of 'P$^2$OT: Progressive Partial Optimal Transport for Deep Imbalanced Clustering'. (Accepted by ICLR 2024)

This tool helps researchers and data scientists improve the accuracy of image classification and recognition when working with datasets where some categories have far fewer examples than others. You input your imbalanced image dataset, and it outputs a more robust clustering model that can better identify objects or features in underrepresented classes. This is ideal for those building computer vision models for diverse real-world scenarios.

About SPPOT

rhfeiyang/SPPOT

Official implementation of 'SP$^2$OT: Semantic-Regularized Progressive Partial Optimal Transport for Imbalanced Clustering'.