Intelligent vehicles need to detect new classes of traffic objects while keeping the performance of old ones. Deep convolution neural network (DCNN) based detector has shown superior performance, however, DCNN is ill-equipped for incremental learning, i.e., a DCNN based vehicle detector trained on traffic sign dataset will catastrophic forget how to detect vehicles. In this paper, we propose a novel method to alleviate this problem, our key insight is that the original class of objects also appears in new task data, by utilizing these objects, our method effectively keeps the detection accuracy of original models while incremental learning to detect new classes of objects. Detailed experiments on PASCAL VOC dataset and TSD-max database verified the effectiveness of our method.
Learn to Detect Objects Incrementally
2018-06-01
3187171 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
IuD Bahn | 2006
|Incrementally Variable High-Voltage Supply
NTRS | 1985
|Large and Small Incrementally Launched Structures
Online Contents | 2000
|Large and Small Incrementally Launched Structures
Transportation Research Record | 2000
|