CIFAR-100-C
PulseAugur coverage of CIFAR-100-C — every cluster mentioning CIFAR-100-C across labs, papers, and developer communities, ranked by signal.
3 day(s) with sentiment data
-
New framework DRO-Augment improves neural network calibration with Mixup augmentation
Researchers have developed DRO-Augment, a new framework designed to improve the calibration of deep neural networks when using Mixup-based data augmentation. This method integrates Wasserstein Distributionally Robust Op…
-
New SA-SAM method improves deep neural network robustness at high sparsity
Researchers have developed Sparsity-Adaptive Sharpness-Aware Minimization (SA-SAM), a new method to improve the robustness of deep neural networks against common corruptions, especially at high sparsity levels. SA-SAM a…
-
Research Questions Identifiability of AI Model Adaptation From Unlabeled Data
A new research paper explores the identifiability of test-time adaptation (TTA) from unlabeled evidence. The study questions whether the available unlabeled data is sufficient to reliably select the best adaptation stra…
-
New method enables conformal prediction transfer across domains
Researchers have developed a novel method called Transported Conformal Calibration (TCC) to address the challenge of conformal prediction when labeled calibration data is only available in a source domain, but predictio…
-
Interleaved noise injection boosts neural network performance on clean and corrupted data
Researchers have developed a novel technique called interleaved noise injection for training neural networks, which surprisingly improves performance on clean, corrupted, and out-of-distribution data. This method altern…
-
New attack targets test-time adaptation models stealthily
Researchers have developed a new method for sample-wise targeted adversarial attacks specifically designed for test-time adaptation (TTA) scenarios. This approach aims to misclassify only specific inputs containing an a…