label smoothing
PulseAugur coverage of label smoothing — every cluster mentioning label smoothing across labs, papers, and developer communities, ranked by signal.
2 day(s) with sentiment data
-
New framework robustly attributes synthetic image sources using dual-branch approach
Researchers have developed a novel framework for attributing the source of synthetic images, addressing the challenge of distribution shifts caused by post-processing. The proposed dual-branch system combines a semantic…
-
New FedLAS algorithm improves neural network calibration
Researchers have developed FedLAS, a novel algorithm designed to improve the calibration of neural network classifiers. This plug-and-play method addresses issues where a model's predicted confidence does not align with…
-
New framework unifies and optimizes robust supervised learning methods
Researchers have developed a unified framework for robust supervised learning that combines various existing methods like distributionally robust optimization and Mixup. This new approach organizes these techniques alon…
-
CutMix training protocol induces spatial locality in Vision Transformers
Researchers have found that specific training techniques can encourage spatial locality in Vision Transformers. By using a 'Modern' protocol involving data augmentation like CutMix and ColorJitter, along with label smoo…