Traditional object detectors are ill-equipped for incremental learning. However, fine-tuning
directly on a well-trained detection model with only new data will lead to catastrophic …

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 …

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 …