Few-Shot Class Incremental Learning via Robust Transformer Approach

1 code implementation • 8 May 2024 • Naeem Paeedeh, Mahardhika Pratama, Sunu Wibirama, Wolfgang Mayer, Zehong Cao, Ryszard Kowalczyk

This problem remains an open problem because all recent works are built upon the convolutional neural networks performing sub-optimally compared to the transformer approaches.

Data Augmentation Few-Shot Class-Incremental Learning +1

Cross-Domain Few-Shot Learning via Adaptive Transformer Networks

1 code implementation • 25 Jan 2024 • Naeem Paeedeh, Mahardhika Pratama, Muhammad Anwar Ma'sum, Wolfgang Mayer, Zehong Cao, Ryszard Kowlczyk

Most few-shot learning works rely on the same domain assumption between the base and the target tasks, hindering their practical applications.

cross-domain few-shot learning

Improving the Backpropagation Algorithm with Consequentialism Weight Updates over Mini-Batches

no code implementations • 11 Mar 2020 • Naeem Paeedeh, Kamaledin Ghiasi-Shirazi

Many attempts took place to improve the adaptive filters that can also be useful to improve backpropagation (BP).