Benchmarking Continual Learning Methods for Image Classification Tasks

Mammoth is a framework for is a framework for Continual Learning research. With more than 70 methods and 20 datasets, it includes the most complete list of competitors and benchmarks for research purposes. This thesis aims to experiment and benchmark a set (5-10) of continual learning techniques for image classification tasks.

The objective is to benchmark the most famous continual learning methods for image classification tasks, and highlight their properties. According to the student’s preference, the task could be changed to detection or segmentation rather than classification. State-of-the-art techniques in continual learning include rehearsal methods such as Experience Replay, Dark Experience Replay, Learning without Forgetting, and so on… The Mammoth framework for continual learning should be used. These methods (at least 5 or 6) should be tested on benchmark and/or real-world datasets. This will depend on the student’s passions. The thesis will consist of a first phase of literature review to fully understand how these methods work, followed by a phase of coding and experimentation.

Under the guidance of a team of researchers, the student will first be required to study recent works on the subject before being practically introduced to the task by experimenting with existing code.

• The candidate should have good programming skills (Python and PyTorch) and be motivated. A previous knowledge of the topic would be preferred but not required.

1. Rolnick D., “Experience Replay for Continual learning”, Advances in Neural Information Processing Systems 32 (NeurIPS 2019), 2019
2. Buzzega P., “Dark experience for general continual learning: a strong, simple baseline”, Advances in Neural Information Processing Systems 32 (NeurIPS 2020), 2020
3. Li Z., “Learning without Forgetting”, IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017