Multi-View Correlation Distillation for Incremental Object Detection
In real applications, new object classes often emerge after the detection model has been trained on a prepared dataset with fixed classes. Due to the storage burden and the privacy of old data, sometimes it is impractical to train the model from scratch with both old and new data. Fine-tuning the old model with only new data will lead to a well-known phenomenon of catastrophic forgetting, which severely degrades the performance of modern object detectors. In this paper, we propose a novel \textbf{M}ulti-\textbf{V}iew \textbf{C}orrelation \textbf{D}istillation (MVCD) based incremental object detection method, which explores the correlations in the feature space of the two-stage object detector (Faster R-CNN). To better transfer the knowledge learned from the old classes and maintain the ability to learn new classes, we design correlation distillation losses from channel-wise, point-wise and instance-wise views to regularize the learning of the incremental model. A new metric named Stability-Plasticity-mAP is proposed to better evaluate both the stability for old classes and the plasticity for new classes in incremental object detection. The extensive experiments conducted on VOC2007 and COCO demonstrate that MVCD can effectively learn to detect objects of new classes and mitigate the problem of catastrophic forgetting.
Code (0)
등록된 구현이 없습니다.
Tasks
Objectobject-detectionObject DetectionSimilar Papers 제목 키워드 기반
Multi-Task Incremental Learning for Object Detection
Multi-task learns multiple tasks, while sharing knowledge and computation among them. However, it suffers from catastrophic forgetting of previous knowledge when learned incrementally without access to the old data. Most…
Incremental LearningObjectobject-detectionObject DetectionFaster ILOD: Incremental Learning for Object Detectors based on Faster RCNN
The human vision and perception system is inherently incremental where new knowledge is continually learned over time whilst existing knowledge is retained. On the other hand, deep learning networks are ill-equipped for …
Incremental LearningKnowledge DistillationObjectRegion ProposalResponse-based Distillation for Incremental Object Detection
Traditional object detection are ill-equipped for incremental learning. However, fine-tuning directly on a well-trained detection model with only new data will leads to catastrophic forgetting. Knowledge distillation is …
Incremental LearningKnowledge DistillationObjectobject-detection+2Overcoming Catastrophic Forgetting in Incremental Object Detection via Elastic Response Distillation
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 forgetting. Knowledge distillation is a…
Class-Incremental Object DetectionIncremental LearningKnowledge Distillationobject-detection+1Two-Level Residual Distillation based Triple Network for Incremental Object Detection
Modern object detection methods based on convolutional neural network suffer from severe catastrophic forgetting in learning new classes without original data. Due to time consumption, storage burden and privacy of old d…
Incremental LearningObjectobject-detectionObject Detection+1