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.
翻译:在实际应用中,在探测模型经过固定等级的预制数据集培训后,往往会出现新的对象类别。由于存储负担和旧数据的隐私,有时用旧和新数据从零开始对模型进行训练是不切实际的。用新数据对旧模型进行微调将导致众所周知的灾难性遗忘现象,这严重地降低了现代物体探测器的性能。在本文中,我们建议采用一种新型的\ textbf{M}M}ulti-textbf{V}ltbf{V}lextbf{C}{C}rextbf{C}orrelation\ textbf{D}(MVCD)基于渐进式物体探测方法,该方法探索了两阶段物体探测器(Aster R-CNN)特性空间的关联性关系。为了更好地转让从旧星级学到的知识并保持学习新等级的能力,我们设计了一种从频道、点和实例角度的蒸馏损失来规范渐进式模型的学习。一个新的指标名为稳定-弹性-AP}基于渐进式的物体探测方法,以更好地评估两阶段天体探测器的稳定性和新级的老级的老级,以便测量老级的老级和塑料的老级的老级的逐渐探测。