CIFAR-100-LT
PulseAugur coverage of CIFAR-100-LT — every cluster mentioning CIFAR-100-LT across labs, papers, and developer communities, ranked by signal.
2 day(s) with sentiment data
-
New study compares mini-batch sampling for long-tailed image classification
A new study on arXiv investigates mini-batch sampling strategies for long-tailed image classification tasks, focusing on the CIFAR-100-LT dataset. Researchers compared uniform instance sampling, class-balanced sampling,…
-
New DirMixE method enhances long-tail recognition in AI models
Researchers have introduced DirMixE, a novel Mixture-of-Expert (MoE) strategy designed to improve recognition of long-tail datasets where test label distributions are unknown and imbalanced. This approach addresses both…
-
CLEAR framework enhances long-tailed classification reliability
Researchers have introduced CLEAR, a novel ensemble framework designed to improve reliability in long-tailed classification tasks. This method generates diverse experts using structured sampling and then estimates a cla…
-
New BS-cRT Method Boosts Long-Tailed Recognition Accuracy
Researchers have developed a new baseline method called BS-cRT for long-tailed recognition tasks, which aims to improve accuracy by retraining only the classifier after initial training. This two-stage procedure involve…
-
New research advances diffusion models for image editing, data augmentation, and unlearning
Researchers are exploring advanced techniques for diffusion models, focusing on improving image editing, data augmentation, and unlearning capabilities. New methods aim to enhance stability and fidelity in image editing…
-
New research tackles deep learning bias, training dynamics, and reliability
Researchers are exploring new theoretical frameworks and practical methods to improve deep learning models. One paper introduces DISCO, a technique for mitigating dataset bias by estimating conditional distance correlat…
-
New method tackles catastrophic forgetting in long-tailed incremental learning
Researchers have developed a new method for robust long-tailed incremental learning, addressing the challenge of sequential learning with imbalanced datasets. The proposed techniques include gradient consistency regular…