Imagenet C
PulseAugur coverage of Imagenet C — every cluster mentioning Imagenet C across labs, papers, and developer communities, ranked by signal.
8 day(s) with sentiment data
-
DOME method learns domain variables for improved test-time adaptation
Researchers have developed DOME, a new method for test-time adaptation that explicitly models domain variables from sparse supervision. Unlike previous approaches that infer a single global domain distribution, DOME use…
-
Self-Soupervision enables model soups from unlabeled data
Researchers have developed a new method called Self-Soupervision, which allows for the creation of "model soups" using self-supervised learning (SSL) instead of traditional supervised learning. This technique enables th…
-
New research probes test-time adaptation challenges in accuracy and latency
Three new research papers explore the nuances of test-time adaptation (TTA) in machine learning. One paper investigates the trade-off between recognizing in-distribution data and detecting out-of-distribution data, find…
-
New method combats prediction bias in AI medical imaging
Researchers have identified a critical failure mode in test-time adaptation methods, known as model collapse, where class clusters merge and lead to prediction bias. They propose a new objective, Distribution Shift Bias…
-
New research advances differential privacy in ML for adaptation and testing
Researchers are developing new methods to ensure differential privacy in machine learning tasks, particularly for hypothesis testing and test-time adaptation. One paper introduces differentially private versions of popu…
-
New attack framework targets AI models with theoretical guarantees
Researchers have developed a new framework for adversarial attacks on AI models, focusing on hard-label black-box scenarios where only the top prediction is accessible. Their approach introduces a novel zero-query initi…
-
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…
-
New losses achieve Neural Collapse faster in supervised learning
Researchers have introduced new methods, NTCE and NONL, to improve supervised classification by achieving Neural Collapse (NC) more efficiently. These techniques address limitations in existing paradigms like cross-entr…
-
MoASE++ advances continual test-time adaptation with expert mixture
Researchers have developed MoASE++, a novel approach for continual test-time adaptation in computer vision tasks. This method utilizes a mixture-of-experts architecture to disentangle domain-agnostic structural features…
-
New framework uses VLM distillation for stable continual model adaptation
Researchers have introduced Test-Time Distillation (TTD), a novel approach to address performance degradation in deep neural networks due to distribution shifts during deployment. Existing methods often suffer from pred…
-
New latent denoising method enhances visual alignment in large multimodal models
Researchers have developed a new latent denoising framework to enhance visual alignment in Large Multimodal Models (LMMs). This method introduces a form of visual supervision by corrupting and then denoising projected v…