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 …
D Yang, Y Zhou, X Hong, A Zhang, X Wei… - Proceedings of the 31st …, 2023 - dl.acm.org
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 …
T Feng, M Wang, H Yuan - … of the IEEE/CVF conference on …, 2022 - openaccess.thecvf.com
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 …
N Dong, Y Zhang, M Ding… - Advances in Neural …, 2021 - proceedings.neurips.cc
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 …