2 papers
cs.CV2024
Long-Tailed Anomaly Detection with Learnable Class Names
Chih-Hui Ho, Kuan-Chuan Peng, Nuno Vasconcelos
Anomaly detection (AD) aims to identify defective images and localize their defects (if any). Ideally, AD models should be able to detect defects over many image classes; without r…
cs.CV2023
Toward Unsupervised Realistic Visual Question Answering
Yuwei Zhang, Chih-Hui Ho, Nuno Vasconcelos
The problem of realistic VQA (RVQA), where a model has to reject unanswerable questions (UQs) and answer answerable ones (AQs), is studied. We first point out 2 drawbacks in curren…