You Rim Choi

Let the Void Be Void: Robust Open-Set Semi-Supervised Learning via Selective Non-Alignment

Open-set semi-supervised learning (OSSL) leverages unlabeled data containing both in-distribution (ID) and unknown out-of-distribution (OOD) samples, aiming simultaneously to improve closed-set accuracy and detect novel OOD instances. Existing methods either discard valuable information from uncerta