Supervised contrastive learning with multiple positive examples
PulseAugur coverage of Supervised contrastive learning with multiple positive examples — every cluster mentioning Supervised contrastive learning with multiple positive examples across labs, papers, and developer communities, ranked by signal.
3 day(s) with sentiment data
-
AI model improves Alzheimer's detection using brain morphology
Researchers have developed a novel deep learning approach to improve the detection of Alzheimer's disease from 3D MRI scans. The method focuses on single domain generalization, enabling models trained on one dataset to …
-
New method improves CEFR level assessment in text across languages
Researchers have developed a novel approach for automatically assessing CEFR levels in text, addressing challenges like imbalanced data and ambiguous level boundaries. Their method combines focal loss to handle underrep…
-
New contrastive learning method optimizes representation geometry for imbalanced datasets
Researchers have developed a new theoretical framework to understand representation geometry in supervised contrastive learning, particularly for datasets with long-tailed distributions. Their analysis revealed that exi…
-
Geospatial AI models show shortcut learning, hindering cross-disaster assessment
A new research paper published on arXiv investigates shortcut learning in geospatial foundation models used for disaster damage assessment. The study found that models trained on familiar disasters often rely on event o…
-
Domain adaptation efficacy depends on pre-trained model's domain knowledge
A new study investigates the effectiveness of domain adaptation techniques when using frozen pre-trained language model backbones for sentiment analysis. The research evaluated different adaptation methods like DANN, MM…
-
Research links AI grokking delay to representational structure formation
Researchers have investigated the phenomenon of grokking, where a model generalizes long after its training data has been fully memorized. Through experiments with a one-layer transformer, they causally demonstrated tha…
-
New OSCS-SupCon framework enhances feature disentanglement in contrastive learning
Researchers have developed a new framework called OSCS-SupCon to improve supervised contrastive learning. This method addresses limitations in existing approaches, such as negative-sample dilution and feature entangleme…
-
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…
-
Researchers explore supervised contrastive learning for deepfake audio detection
Researchers have explored supervised contrastive learning techniques to improve deepfake audio detection. Their study focused on varying similarity metrics, such as cosine and angular similarity, and different methods f…
-
Contrastive learning advances model robustness and transparency in AI
Contrastive learning is a machine learning technique that creates an embedding space where similar data points are grouped together and dissimilar ones are separated. This method can be applied in both supervised and un…