Anno-incomplete Multi-dataset Detection
This addresses the challenge of needing new datasets for object detection tasks due to incomplete annotations across existing datasets, though it is incremental in nature.
The paper tackles the problem of object detection when using multiple datasets with incomplete and heterogeneous annotations, proposing an end-to-end multi-task learning architecture that improves mAP by 2.17% on COCO and 2.10% on VOC.
Object detectors have shown outstanding performance on various public datasets. However, annotating a new dataset for a new task is usually unavoidable in real, since 1) a single existing dataset usually does not contain all object categories needed; 2) using multiple datasets usually suffers from annotation incompletion and heterogeneous features. We propose a novel problem as "Annotation-incomplete Multi-dataset Detection", and develop an end-to-end multi-task learning architecture which can accurately detect all the object categories with multiple partially annotated datasets. Specifically, we propose an attention feature extractor which helps to mine the relations among different datasets. Besides, a knowledge amalgamation training strategy is incorporated to accommodate heterogeneous features from different sources. Extensive experiments on different object detection datasets demonstrate the effectiveness of our methods and an improvement of 2.17%, 2.10% in mAP can be achieved on COCO and VOC respectively.