Weakly Supervised One Shot Segmentation

One-shot learning is a challenging discipline of machine learning since it gnaws at the concept of learning from large amounts of data. This is akin to making machine learning algorithms generalize from a few examples, much like how humans learn. We explore another novel dimension to this problem, o...

Full description

Saved in:
Bibliographic Details
Main Authors: Raza, Hasnain, Ravanbakhsh, Mahdyar, Klein, Tassilo, Nabi, Moin
Format: Conference Proceeding
Language:English
Subjects:
Feature extraction
Few shot
Image segmentation
Machine learning
one shot
Prototypes
segmentation
semantic segmentation
Task analysis
Testing
Training
weakly supervised
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:One-shot learning is a challenging discipline of machine learning since it gnaws at the concept of learning from large amounts of data. This is akin to making machine learning algorithms generalize from a few examples, much like how humans learn. We explore another novel dimension to this problem, of using weak supervision (labels only) in the one-shot domain, and specifically analyse it in the context of semantic segmentation. This is a challenging problem since we operate in the scarcity of data and supervision. We present a simple yet effective approach, whereby exploiting information from the base training classes in the current one-shot segmentation set-up allows for weak supervision to be easily used. We show that this strategy can be leveraged to achieve nearly the same results as full supervision, but with no pixel annotations, allowing fully automated segmentation. Comparisons to several fully supervised methods show convincing results. As well as better results than a weakly supervised baseline. Also presented is a baseline for generalized segmentation under one-shot and weak supervision assumptions.
ISSN:2473-9944
DOI:10.1109/ICCVW.2019.00176