Open Peer Review. Open Publishing. Open Access. Open Discussion. Open Directory. Open Recommendations. Open API. Open Source.
Conditional Networks for Few-Shot Semantic Segmentation
Kate Rakelly, Evan Shelhamer, Trevor Darrell, Alyosha Efros, Sergey Levine
Feb 12, 2018 (modified: Feb 12, 2018)ICLR 2018 Workshop Submissionreaders: everyone
Abstract:Few-shot learning methods aim for good performance in the low-data regime.
Structured output tasks such as segmentation present difficulties for few-shot
learning because of their high dimensionality and the statistical dependencies
among outputs. To tackle this problem, we propose the co-FCN, a conditional
network learned by end-to-end optimization to perform fast, accurate few-shot
segmentation. The network conditions on an annotated support set of images via
feature fusion to perform inference on an unannotated query image. Once learned,
our conditioning approach requires no further optimization for new data. Addi-
tional annotated inputs are used to update the output via a single inference step,
making the model suitable for interactive use. Our conditional network signifi-
cantly improves few-shot accuracy over the prior state-of-the-art.
TL;DR:We propose a conditional network learned end-to-end to perform few-shot semantic segmentation
Keywords:semantic segmentation, few-shot learning
Enter your feedback below and we'll get back to you as soon as possible.