Incremental object detection (IOD) aims to train an object detector in phases, each with annotations for new object categories. As other incremental settings, IOD is subject to …
Incremental learning requires a model to continually learn new tasks from streaming data. However, traditional fine-tuning of a well-trained deep neural network on a new task will …
In a real-world setting, object instances from new classes can be continuously encountered by object detectors. When existing object detectors are applied to such scenarios, their …
Deep learning models tend to forget their earlier knowledge while incrementally learning new tasks. This behavior emerges because the parameter updates optimized for the new …
In real applications, new object classes often emerge after the detection model has been trained on a prepared dataset with fixed classes. Fine-tuning the old model with only new …
The human vision and perception system is inherently incremental where new knowledge is continually learned over time whilst existing knowledge is retained. On the other hand, deep …
F Cermelli, A Geraci, D Fontanel… - Proceedings of the …, 2022 - openaccess.thecvf.com
Despite the recent advances in the field of object detection, common architectures are still ill- suited to incrementally detect new categories over time. They are vulnerable to catastrophic …
Elastic weight consolidation (EWC) has been successfully applied for general incremental learning to overcome the catastrophic forgetting issue. It adaptively constrains each …
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 …