The paper introduces GloFND, an optimization-based method that learns a threshold for each anchor image during training to automatically detect false negative pairs in self-supervised contrastive learning. Unlike prior approaches that only consider false negatives within a mini-batch, GloFND globally identifies them across the entire dataset while keeping per-iteration computation independent of dataset size. Experiments on image and image-text data show the method’s effectiveness, and the implementation is publicly available.
By Vicente Balmaseda, Bokun Wang, Ching-Long Lin, Tianbao Yang
arXiv:2606. 28598v1 Announce Type: cross Abstract: Prediction sets should have high coverage to be useful, but some coverage notions are more practically relevant than others.
By Aabesh Bhattacharyya, Tiffany Ding, Rina Foygel Barber
arXiv:2606. 31577v1 Announce Type: cross Abstract: Conformal predictions have attracted significant attention in the field of uncertainty quantification, mainly because of their strong marginal coverage guarantees.
By Cl\'ement Fuchs, Tim Bary, Beno\^it Macq
arXiv:2605.08506v3 Announce Type: replace
Abstract: Robust optimization (RO) provides a principled framework for decision-making under uncertainty, but its performance critically depends on the choic...
By Shuyi Chen, Wenbin Zhou, Shixiang Zhu
arXiv:2602. 01733v3 Announce Type: replace-cross Abstract: Conformal Prediction (CP) provides a statistical framework for uncertainty quantification that constructs prediction sets with coverage guarantees.
By Junxian Liu, Hao Zeng, Hongxin Wei
arXiv:2609.37298v1 Announce Type: new
Abstract: Conformal prediction provides set-valued predictions with distribution-free coverage guarantees, making it attractive for high-stakes image classificat...
By Julio Silva-Rodr\'iguez, Ender Konukoglu
arXiv:2501.18060v2 Announce Type: replace-cross
Abstract: Conformal inference provides a rigorous statistical framework for uncertainty quantification in machine learning, enabling well-calibrated pr...
By Teresa Bortolotti, Y. X. Rachel Wang, Xin Tong, Alessandra Menafoglio, Simone Vantini, Matteo Sesia
arXiv:2606. 26973v1 Announce Type: cross Abstract: Open-set semi-supervised learning aims to leverage unlabeled data that may contain out-of-distribution outliers while maintaining performance on in-distribution classes.
By Jiahe Chen, Qian Shao, Qiyuan Chen, Jiaying He, Jintai Chen, Jian Wu, Hongxia Xu
The paper introduces a tail‑aware geometry learning framework for multivariate conformal prediction using ellipsoids. It decouples tail sensitivity from coverage guarantees by learning a metric matrix through volume minimization under a CVaR constraint, followed by standard conformal calibration. The approach is convex, prioritizes high‑residual samples, and theoretically balances ellipsoidal volume against tail severity, with experiments confirming its effectiveness.
By Xiang Zhang
arXiv:2608.22679v1 Announce Type: new
Abstract: Semantic segmentation has rapidly advanced with deep learning; however, challenges remain in effectively capturing local and global contexts as well as...
By Changki Sung, Hyungtae Lim, Wanhee Kim, Youngwoo Seo, Hyun Myung
arXiv:2603. 15263v2 Announce Type: replace-cross Abstract: Self-supervised learning (SSL) has revolutionized representation learning, with Joint-Embedding Architectures (JEAs) emerging as an effective approach for capturing semantic features.
By Konstantinos Almpanakis, Anna Kreshuk
arXiv:2601. 02998v2 Announce Type: replace Abstract: In many fairness and distribution robustness problems, one has access to labeled data from multiple source distributions yet the test data may come from an arbitrary member or a mixture of them.
By Yuqi Yang, Ying Jin