Contrast R-CNN for Continual Learning in Object Detection
The continual learning problem has been widely studied in image classification, while rare work has been explored in object detection. Some recent works apply knowledge distillation to constrain the model to retain old knowledge, but this rigid constraint is detrimental for learning new knowledge. In our paper, we propose a new scheme for continual learning of object detection, namely Contrast R-CNN, an approach strikes a balance between retaining the old knowledge and learning the new knowledge. Furthermore, we design a Proposal Contrast to eliminate the ambiguity between old and new instance to make the continual learning more robust. Extensive evaluation on the PASCAL VOC dataset demonstrates the effectiveness of our approach.
Code (0)
등록된 구현이 없습니다.
Tasks
Continual Learningimage-classificationImage ClassificationKnowledge DistillationObjectobject-detectionObject DetectionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Label-Efficient Online Continual Object Detection in Streaming Video
Humans can watch a continuous video stream and effortlessly perform continual acquisition and transfer of new knowledge with minimal supervision yet retaining previously learnt experiences. In contrast, existing continua…
Continual LearningHippocampusObjectobject-detection+1Seeing Objects in dark with Continual Contrastive Learning
Object Detection, a fundamental computer vision problem, has paramount importance in smart camera systems. However, a truly reliable camera system could be achieved if and only if the underlying object detection componen…
Continual LearningContrastive LearningImage EnhancementObject+2MR-GDINO: Efficient Open-World Continual Object Detection
Open-world (OW) recognition and detection models show strong zero- and few-shot adaptation abilities, inspiring their use as initializations in continual learning methods to improve performance. Despite promising results…
Continual Learningobject-detectionObject DetectionCOOLer: Class-Incremental Learning for Appearance-Based Multiple Object Tracking
Continual learning allows a model to learn multiple tasks sequentially while retaining the old knowledge without the training data of the preceding tasks. This paper extends the scope of continual learning research to cl…
class-incremental learningClass Incremental LearningContinual LearningDisentanglement+4Exploring Test-Time Adaptation for Object Detection in Continually Changing Environments
Real-world application models are commonly deployed in dynamic environments, where the target domain distribution undergoes temporal changes. Continual Test-Time Adaptation (CTTA) has recently emerged as a promising tech…
Contrastive LearningObjectobject-detectionObject Detection+1