SubPopMark embeds verifiable subpopulation biases into distilled datasets via CVM and USTM optimization stages, allowing provenance inference through comparison of model output signatures against a reference behavior bank.
Reading digits in natural images with unsupervised feature learning
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3representative citing papers
MahaVar augments the Mahalanobis OOD score with class-wise distance variance, which is theoretically higher for in-distribution samples under relaxed Neural Collapse geometry.
Proposes LCD and three other hybrid uncertainty-diversity sampling methods for active learning that outperform prior approaches by selecting uncertain yet diverse samples.
citing papers explorer
-
From Compression to Accountability: Harmless Copyright Protection for Dataset Distillation
SubPopMark embeds verifiable subpopulation biases into distilled datasets via CVM and USTM optimization stages, allowing provenance inference through comparison of model output signatures against a reference behavior bank.
-
MahaVar: OOD Detection via Class-wise Mahalanobis Distance Variance under Neural Collapse
MahaVar augments the Mahalanobis OOD score with class-wise distance variance, which is theoretically higher for in-distribution samples under relaxed Neural Collapse geometry.
-
Balancing Uncertainty and Diversity of Samples: Leveraging Diversity of Least, High Confidence Samples for Effective Active Learning
Proposes LCD and three other hybrid uncertainty-diversity sampling methods for active learning that outperform prior approaches by selecting uncertain yet diverse samples.