← Search

HyeongGwon Hong

2 accepted papers

2025

Controllable Feature Whitening for Hyperparameter-Free Bias Mitigation

ICCV 2025poster

As the use of artificial intelligence rapidly increases, the development of trustworthy artificial intelligence has become important. However, recent studies have shown that deep neural networks are susceptible to learn spurious correlations present in datasets. To improve the reliability, we propos…

Cited by 0SourcePDFScholar
2024

Self-supervised Transformation Learning for Equivariant Representations

NeurIPS 2024poster

Unsupervised representation learning has significantly advanced various machine learning tasks. In the computer vision domain, state-of-the-art approaches utilize transformations like random crop and color jitter to achieve invariant representations, embedding semantically the same inputs despite tr…