← Search

Kwanhyung Lee

2 accepted papers

2026

Soft Equivariance Regularization for Invariant Self-Supervised Learning

ICLR 2026poster

A central principle in self-supervised learning (SSL) is to learn data representations that are invariant to semantic-preserving transformations \eg, image representations should remain unchanged under augmentations like cropping or color jitter. While effective for classification, such invariance c…

Cited by 0SourcecodeScholar
2024

Compact and De-Biased Negative Instance Embedding for Multi-Instance Learning on Whole-Slide Image Classification

ICASSP 2024accepted

Whole-slide image (WSI) classification is a challenging task because 1) patches from WSI lack annotation, and 2) WSI possesses unnecessary variability, e.g., stain protocol. Recently, Multiple-Instance Learning (MIL) has made significant progress, allowing for classification based on slide-level, ra…

Cited by 0SourceScholar