Modern object detectors are ill-equipped to incrementally learn new emerging object
classes over time due to the well-known phenomenon of catastrophic forgetting. Due to data …

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 …

Incremental object detection (IOD) aims to mitigate catastrophic forgetting for object
detectors when incrementally learning to detect new emerging object classes without using …

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 …

As a basic component in multimedia applications, object detectors are generally trained on a
fixed set of classes that are pre-defined. However, new object classes often emerge after the …

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 …

Deep networks have shown remarkable results in the task of object detection. However, their
performance suffers critical drops when they are subsequently trained on novel classes …

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 …

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 …

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 …