返回
Towards Open-Set Scene Graph Generation With Unknown Objects
DOI:10.1109/ACCESS.2022.3145465.png)
摘要
En 中文
Scene graph generation (SGG) aims to detect objects and their relationships in an image, thereby enabling a detailed understanding of a complex scene for various real-world applications. In SGG applications such as robot vision, it is important to correctly detect all objects without recognizing any object as another kind of object or ignoring it. However, previous studies on SGG do not consider unknown objects whose classes are unseen in training. Consequently, current SGG methods wrongly classify them as known object classes or overlook them. In this paper, we propose a new problem named open-set SGG with unknown objects, focusing on detecting even unknown objects and their relationships. Specifically, we formally define this new problem and propose an evaluation protocol, including an extended dataset with unknown objects and novel evaluation metrics designed for the open-set setting. We also build baseline methods by employing and extending existing SGG methods and compare them through experiments to establish the current baseline performance of open-set SGG. Finally, we discuss the limitations of the current SGG methodology in the open-set setting and point out future research directions.
Keyword:
Object detection
Training
Image recognition
Training data
Protocols
Robots
Predictive models
Scene graph generation
open-set
object detection
期刊
IF:
3.6
论文数:
9.8W
被引数:
29.4W
机构
引用论文
Nail fold capillaroscopy differs widely between systemic sclerosis and chronic graft vs host disease of the skin
Rheumatology
IF0
Photoperiodic effects in the Djungarian hamster: one minute of light during darktime mimics influence of long photoperiods on testicular recrudescence, body weight and pelage colour
Experientia
IF0
Hematological and serum biochemical analytes reflect physiological challenges during gestation and lactation in killer whales (Orcinus orca)
Zoo Biology
IF0


