Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Deep Metric Learning for Open World Semantic Segmentation

About

Classical close-set semantic segmentation networks have limited ability to detect out-of-distribution (OOD) objects, which is important for safety-critical applications such as autonomous driving. Incrementally learning these OOD objects with few annotations is an ideal way to enlarge the knowledge base of the deep learning models. In this paper, we propose an open world semantic segmentation system that includes two modules: (1) an open-set semantic segmentation module to detect both in-distribution and OOD objects. (2) an incremental few-shot learning module to gradually incorporate those OOD objects into its existing knowledge base. This open world semantic segmentation system behaves like a human being, which is able to identify OOD objects and gradually learn them with corresponding supervision. We adopt the Deep Metric Learning Network (DMLNet) with contrastive clustering to implement open-set semantic segmentation. Compared to other open-set semantic segmentation methods, our DMLNet achieves state-of-the-art performance on three challenging open-set semantic segmentation datasets without using additional data or generative models. On this basis, two incremental few-shot learning methods are further proposed to progressively improve the DMLNet with the annotations of OOD objects.

Jun Cen, Peng Yun, Junhao Cai, Michael Yu Wang, Ming Liu• 2021

Related benchmarks

TaskDatasetResultRank
Semantic segmentationS3DIS
mIoU70.4
88
Semantic segmentationScanNet V2
mIoU63.5
54
Anomaly DetectionStreetHazards
AP14.7
18
Anomaly DetectionStreetHazards (test)
AP14.7
15
Anomaly SegmentationStreetHazards (test)
FPR9517.3
13
Anomaly DetectionRoad Anomaly
AP37
12
Showing 6 of 6 rows

Other info

Follow for update