Class-Incremental Learning: Survey and Performance Evaluation on Image Classification

For future learning systems, incremental learning is desirable because it allows for: efficient resource usage by eliminating the need to retrain from scratch at the arrival of new data; reduced memory usage by preventing or limiting the amount of data required to be stored - also important when privacy limitations are imposed; and learning that more closely resembles human learning. The main challenge for incremental learning is catastrophic forgetting, which refers to the precipitous drop in performance on previously learned tasks after learning a new one. Incremental learning of deep neural networks has seen explosive growth in recent years. Initial work focused on task-incremental learning, where a task-ID…

• EC
  European Commission

  Award: 951911 - AI4Media
• GD
  Generalitat de Catalunya

  Award: 2019-FI_B2-00189