2 papers
cs.CV2026
Combining Discrepancy-Confusion Uncertainty and Calibration Diversity for Active Fine-Grained Image Classification
Yinghao Jin, Xi Yang
Active learning (AL) aims to build high-quality labeled datasets by iteratively selecting the most informative samples from an unlabeled pool under limited annotation budgets. Howe…
cs.LG2025
Clustering Properties of Self-Supervised Learning
Xi Weng, Jianing An, Xudong Ma +5
Self-supervised learning (SSL) methods via joint embedding architectures have proven remarkably effective at capturing semantically rich representations with strong clustering prop…