An experimental approach on Few Shot Class Incremental Learning
This work addresses incremental learning with limited data for machine learning models, but it appears incremental as it builds on existing methods without introducing a new paradigm.
The paper tackles the problem of Few-Shot Class-Incremental Learning (FSCIL) by evaluating existing methods and proposing an experimental approach that replaces the CLIP visual-language model with CLOOB to improve performance, though no concrete results or numbers are provided.
Few-Shot Class-Incremental Learning (FSCIL) represents a cutting-edge paradigm within the broader scope of machine learning, designed to empower models with the ability to assimilate new classes of data with limited examples while safeguarding existing knowledge. The paper will present different solutions which contain extensive experiments across large-scale datasets, domain shifts, and network architectures to evaluate and compare the selected methods. We highlight their advantages and then present an experimental approach with the purpose of improving the most promising one by replacing the visual-language (V-L) model (CLIP) with another V-L model (CLOOB) that seem to outperform it on zero-shot learning tasks. The aim of this report is to present an experimental method for FSCIL that would improve its performance. We also plan to offer an overview followed by an analysis of the recent advancements in FSCIL domain, focusing on various strategies to mitigate catastrophic forgetting and improve the adaptability of models to evolving tasks and datasets.