paper-with-me

Papers

Contrast R-CNN for Continual Learning in Object Detection

2021-07-11 · Kai Zheng, Cen Chen

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.

📄 PDF Abstract BibTeX arXiv:2108.04224

Code (0)

등록된 구현이 없습니다.

Tasks

Continual Learningimage-classificationImage ClassificationKnowledge DistillationObjectobject-detectionObject Detection

Methods 이 논문이 사용한 방법론

Knowledge Distillation A very simple way to improve the performance of almost any machine learning algorithm is to train many different models on the same data and then to average their predictions.…

Similar Papers 제목 키워드 기반

Label-Efficient Online Continual Object Detection in Streaming Video

2022-06-01 · ICCV 2023 1 · Jay Zhangjie Wu, David Junhao Zhang, Wynne Hsu, Mengmi Zhang 외

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+1

Seeing Objects in dark with Continual Contrastive Learning

2021-12-06 · Ujjal Kr Dutta

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+2

MR-GDINO: Efficient Open-World Continual Object Detection

2024-12-20 · Bowen Dong, Zitong Huang, Guanglei Yang, Lei Zhang 외

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 Detection

COOLer: Class-Incremental Learning for Appearance-Based Multiple Object Tracking

2023-10-04 · Zhizheng Liu, Mattia Segu, Fisher Yu

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+4

Exploring Test-Time Adaptation for Object Detection in Continually Changing Environments

2024-06-24 · Shilei Cao, Yan Liu, Juepeng Zheng, Weijia Li 외

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