10 citations · 23 across the 14 of their papers we have counts for
14 papers
PIP: Prototypes-Injected Prompt for Federated Class Incremental Learning
Muhammad Anwar Ma'sum, Mahardhika Pratama, Savitha Ramasamy +3
Federated Class Incremental Learning (FCIL) is a new direction in continual learning (CL) for addressing catastrophic forgetting and non-IID data distribution simultaneously. Exist…
Unsupervised Few-Shot Continual Learning for Remote Sensing Image Scene Classification
Muhammad Anwar Ma'sum, Mahardhika Pratama, Ramasamy Savitha +3
A continual learning (CL) model is desired for remote sensing image analysis because of varying camera parameters, spectral ranges, resolutions, etc. There exist some recent initia…
Mixup Domain Adaptations for Dynamic Remaining Useful Life Predictions
Muhammad Tanzil Furqon, Mahardhika Pratama, Lin Liu +2
Remaining Useful Life (RUL) predictions play vital role for asset planning and maintenance leading to many benefits to industries such as reduced downtime, low maintenance costs, e…
Towards Cross-Domain Continual Learning
Marcus de Carvalho, Mahardhika Pratama, Jie Zhang +2
Continual learning is a process that involves training learning agents to sequentially master a stream of tasks or classes without revisiting past data. The challenge lies in lever…
Cross-Domain Few-Shot Learning via Adaptive Transformer Networks
Naeem Paeedeh, Mahardhika Pratama, Muhammad Anwar Ma'sum +3
Most few-shot learning works rely on the same domain assumption between the base and the target tasks, hindering their practical applications. This paper proposes an adaptive trans…
Dynamic Long-Term Time-Series Forecasting via Meta Transformer Networks
Muhammad Anwar Ma'sum, MD Rasel Sarkar, Mahardhika Pratama +5
A reliable long-term time-series forecaster is highly demanded in practice but comes across many challenges such as low computational and memory footprints as well as robustness ag…