A survey on continual semantic segmentation: Theory, challenge, method and application

B Yuan, D Zhao - IEEE Transactions on Pattern Analysis and …, 2024 - ieeexplore.ieee.org
Continual learning, also known as incremental learning or life-long learning, stands at the
forefront of deep learning and AI systems. It breaks through the obstacle of one-way training …

Few-Shot Incremental Object Detection in Aerial Imagery via Dual-Frequency Prompt

X Lu, W Diao, J Li, Y Zhang, P Wang… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
Recently, there has been a growing interest in few-shot incremental object detection
(FSIOD). It learns new tasks with limited data while mitigating catastrophic forgetting on …

kNN-CLIP: Retrieval Enables Training-Free Segmentation on Continually Expanding Large Vocabularies

Z Gui, S Sun, R Li, J Yuan, Z An, K Roth… - arXiv preprint arXiv …, 2024 - arxiv.org
Rapid advancements in continual segmentation have yet to bridge the gap of scaling to
large continually expanding vocabularies under compute-constrained scenarios. We …

A Class-Incremental Object Detection Method for Remote Sensing Images Based on Dynamic Multi-Prototype Matching

M Hu, W Yin, W Diao, X Gao… - IEEE Journal of Selected …, 2024 - ieeexplore.ieee.org
In object detection task, incremental learning method enables the previously trained model
better adapt to the new task using either a small amount of old data or none at all. In the …