Learn new objects without forgetting old ones by generate perturbations with new samples with BSDP
Learn new objects without forgetting old ones by generate perturbations with new samples with BSDP
BSDP: Brain-inspired Streaming Dual-level Perturbations for Online Open World Object Detection
arXiv paper abstract https://arxiv.org/abs/2403.02637
arXiv PDF paper https://arxiv.org/pdf/2403.02637.pdf
Humans can … distinguish the known and unknown categories and can recognize the unknown object by learning it once instead of repeating it many times without forgetting the learned object … refer to such a learning manner as OnLine Open World Object Detection(OLOWOD).
… propose a simple plug-and-play method, called Brain-inspired Streaming Dual-level Perturbations(BSDP), to solve the OLOWOD problem.
… first calculate the prototypes of previous categories and use the distance between samples and the prototypes as the sample selecting strategy to choose old samples for replay;
… take the prototypes as the streaming feature-level perturbations of new samples, so as to improve the plasticity of the model through revisiting the old knowledge;
… use the distribution of the features of the old category samples to generate adversarial data in the form of streams as the data-level perturbations to enhance the robustness of the model to new categories.
… the excellent results demonstrate the promising performance of … proposed method and learning manner.
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
LinkedIn https://www.linkedin.com/in/morris-lee-47877b7b
