Learn new objects without forgetting old ones by only replaying old foreground objects with ABR
Learn new objects without forgetting old ones by only replaying old foreground objects with ABR
Augmented Box Replay: Overcoming Foreground Shift for Incremental Object Detection
arXiv paper abstract https://arxiv.org/abs/2307.12427
arXiv PDF paper https://arxiv.org/pdf/2307.12427.pdf
In incremental learning, replaying stored samples from previous tasks together with current task samples is one of the most efficient approaches to address catastrophic forgetting.
However, unlike incremental classification, image replay has not been successfully applied to incremental object detection (IOD).
... identify the overlooked problem of foreground shift as the main reason for this. Foreground shift ... occurs when replaying ... background might contain foreground objects of the current task.
... a novel and efficient Augmented Box Replay (ABR) method is developed that only stores and replays foreground objects and thereby circumvents the foreground shift problem.
... propose an innovative Attentive RoI Distillation loss that uses spatial attention from region-of-interest (RoI) features to constrain current model to focus on the most important information from old model.
... experiments ... support the state-of-the-art performance of ... model.
Please like and share this post if you enjoyed it using the buttons at the bottom!
Stay up to date. Subscribe to my posts https://morrislee1234.wixsite.com/website/contact
Web site with my other posts by category https://morrislee1234.wixsite.com/website
Comments