Related Researcher

Author's Photo

Kim, Kwang In
Machine Learning and Vision Group
Research Interests
  • Neural networks, semi-supervised learning; unsupervised learning; learning on Riemannian manifolds and graph-structured data; human body pose estimation; human hand pose estimation; image and video enhancement.


Active label correction using robust parameter update and entropy propagation

Cited 0 times inthomson ciCited 0 times inthomson ci
Active label correction using robust parameter update and entropy propagation
Kim, Kwang In
Issue Date
ECCV 2022
European Conference on Computer Vision
Label noise is prevalent in real-world visual learning applications and correcting all label mistakes can be prohibitively costly. Training neural network classifiers on such noisy datasets may lead to significant performance degeneration. Active label correction (ALC) attempts to minimize the re-labeling costs by identifying examples for which providing correct labels will yield maximal performance improvements. Existing ALC approaches typically select the examples that the classifier is least confident about (e.g. with the largest entropies). However, such confidence estimates can be unreliable as the classifier itself is initially trained on noisy data. Also, naively selecting a batch of low-confidence examples can result in redundant labeling of spatially adjacent examples. We present a new ALC algorithm that addresses these challenges. Our algorithm robustly estimates label confidence values by regulating the contributions of individual examples in the parameter update of the network. Further, our algorithm avoids redundant labeling by promoting diversity in batch selection through propagating the confidence of each newly labeled example to the entire dataset. Experiments involving four benchmark datasets and two types of label noise demonstrate that our algorithm offers a significant improvement in re-labeling efficiency over state-of-the-art ALC approaches.
Appears in Collections:
AI_Conference Papers
Files in This Item:
There are no files associated with this item.

find_unist can give you direct access to the published full text of this article. (UNISTARs only)

Show full item record


  • mendeley


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.