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

One-Shot Learning for Semantic Segmentation

About

Low-shot learning methods for image classification support learning from sparse data. We extend these techniques to support dense semantic image segmentation. Specifically, we train a network that, given a small set of annotated images, produces parameters for a Fully Convolutional Network (FCN). We use this FCN to perform dense pixel-level prediction on a test image for the new semantic class. Our architecture shows a 25% relative meanIoU improvement compared to the best baseline methods for one-shot segmentation on unseen classes in the PASCAL VOC 2012 dataset and is at least 3 times faster.

Amirreza Shaban, Shray Bansal, Zhen Liu, Irfan Essa, Byron Boots• 2017

Related benchmarks

TaskDatasetResultRank
Few-shot SegmentationPASCAL-5i
mIoU (Fold 0)35.9
325
Semantic segmentationCOCO 2014 (val)
mIoU46.2
251
Few-shot Semantic SegmentationPASCAL-5^i (test)
FB-IoU61.5
177
Semantic segmentationPASCAL-5i
Mean mIoU43.9
111
Semantic segmentationPASCAL-5^i (test)
Mean Score44
107
Semantic segmentationPASCAL 5-shot 5i
Mean mIoU43.95
100
Few-shot SegmentationPASCAL 5i (val)
mIoU (Mean)40.8
83
Semantic segmentationPASCAL-5^i Fold-1
mIoU58.1
75
Semantic segmentationPASCAL-5^i Fold-3
mIoU39.1
75
Semantic segmentationPASCAL-5^i Fold-2
mIoU42.7
75
Showing 10 of 22 rows

Other info

Code

Follow for update