Towards Scalable Image Classifier Learning with Noisy Labels via Domain Adaptation

Kuang-Huei Lee (), Xiaodong He (), Linjun Yang () and Lei Zhang ()
Additional contact information
Kuang-Huei Lee: Microsoft AI and Research
Xiaodong He: JD AI Research
Linjun Yang: Facebook
Lei Zhang: Microsoft Research

Chapter Chapter 9 in Domain Adaptation in Computer Vision with Deep Learning, 2020, pp 159-174 from Springer

Abstract: Abstract In this chapter we focus on learning image classifiers with noisy labels through domain adaptation. Existing approaches for learning image classifiers with noisy labels using human supervision are generally difficult to scale to large set of classes as manual labeling images for all classes are expensive and time-consuming. Approaches that address noisy labels without manual labeling efforts are scalable but less effective in lack of reliable supervision. Transfer learning reconciles this conflict through transferring knowledge from classes with exemplary human supervision (source domains) to classes where data are not manually verified (target domains), relaxing the requirement of human efforts. In this chapter, we introduce a transfer learning set-up for tackling noisy labels, and review CleanNet, the first neural network model that practically implements this set-up, and explore future directions of this topic.

Keywords: Domain adaptation; Label noise; Weakly supervised learning (search for similar items in EconPapers)
Date: 2020
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:sprchp:978-3-030-45529-3_9

Ordering information: This item can be ordered from
http://www.springer.com/9783030455293

DOI: 10.1007/978-3-030-45529-3_9

Access Statistics for this chapter

More chapters in Springer Books from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().