arXiv Analytics

Sign in

arXiv:2104.03309 [cs.CV]AbstractReferencesReviewsResources

Streaming Self-Training via Domain-Agnostic Unlabeled Images

Zhiqiu Lin, Deva Ramanan, Aayush Bansal

Published 2021-04-07Version 1

We present streaming self-training (SST) that aims to democratize the process of learning visual recognition models such that a non-expert user can define a new task depending on their needs via a few labeled examples and minimal domain knowledge. Key to SST are two crucial observations: (1) domain-agnostic unlabeled images enable us to learn better models with a few labeled examples without any additional knowledge or supervision; and (2) learning is a continuous process and can be done by constructing a schedule of learning updates that iterates between pre-training on novel segments of the streams of unlabeled data, and fine-tuning on the small and fixed labeled dataset. This allows SST to overcome the need for a large number of domain-specific labeled and unlabeled examples, exorbitant computational resources, and domain/task-specific knowledge. In this setting, classical semi-supervised approaches require a large amount of domain-specific labeled and unlabeled examples, immense resources to process data, and expert knowledge of a particular task. Due to these reasons, semi-supervised learning has been restricted to a few places that can house required computational and human resources. In this work, we overcome these challenges and demonstrate our findings for a wide range of visual recognition tasks including fine-grained image classification, surface normal estimation, and semantic segmentation. We also demonstrate our findings for diverse domains including medical, satellite, and agricultural imagery, where there does not exist a large amount of labeled or unlabeled data.

Comments: Project Page: https://www.cs.cmu.edu/~aayushb/SST/
Categories: cs.CV, cs.AI, cs.LG
Related articles: Most relevant | Search more
arXiv:1903.12648 [cs.CV] (Published 2019-03-29)
Incremental Learning with Unlabeled Data in the Wild
arXiv:2008.05746 [cs.CV] (Published 2020-08-13)
Adversarial Knowledge Transfer from Unlabeled Data
arXiv:1603.07957 [cs.CV] (Published 2016-03-25)
Object Recognition Based on Amounts of Unlabeled Data