[NeurIPS 2021] Deceive D: Adaptive Pseudo Augmentation for GAN Training with Limited Data

ECCV2018

An analysis and comparison of transfer learning and meta-learning for the task of few-shot classification of flowers with particular interest in cases where data is limited.

Federated prediction of graph multi-trajectory evolution

Heterogeneous federated learning for graph super-resolution

Code to partially reproduce results in "Unearthing InSights into Mars: Unsupervised source separation with limited data", ICML 2023

Artificial-intuition–driven pattern recognition system under high noise & scarce data environments. Validated on real-world datasets with proven generalization, robustness & scalability.

An open source with graphical user interface (GUI) for choosing a minimal sensor set out of analyte-sensor screening data, that preserves both accuracy and minimal sensor number.

This is a python script which generate a dataset by your limited data

This repository contains the code and the report for the coursework of INFR11031 Advanced Vision, a postgraduate course offered at The University of Edinburgh. The task was to train on limited and improve the accuracy of the ResNet-50 classifier on a small subset of the ImageNet dataset containing 50K training images and 50K test images. Achieved a mark of 74%