5 papers
LeVLJEPA: End-to-End Vision-Language Pretraining Without Negatives
Lukas Kuhn, Giuseppe Serra, Randall Balestriero +1
Vision-language pretraining remains dominated by contrastive objectives, whereas vision-only self-supervised learning has largely adopted non-contrastive methods. At the same time,…
Non-Contrastive Vision-Language Learning with Predictive Embedding Alignment
Lukas Kuhn, Giuseppe Serra, Florian Buettner
Vision-language models have transformed multimodal representation learning, yet dominant contrastive approaches like CLIP require large batch sizes, careful negative sampling, and…
Federated Continual Learning Goes Online: Uncertainty-Aware Memory Management for Vision Tasks and Beyond
Giuseppe Serra, Florian Buettner
Given the ability to model more realistic and dynamic problems, Federated Continual Learning (FCL) has been increasingly investigated recently. A well-known problem encountered in…
DATS: Distance-Aware Temperature Scaling for Calibrated Class-Incremental Learning
Giuseppe Serra, Florian Buettner
Continual Learning (CL) is recently gaining increasing attention for its ability to enable a single model to learn incrementally from a sequence of new classes. In this scenario, i…
How to Leverage Predictive Uncertainty Estimates for Reducing Catastrophic Forgetting in Online Continual Learning
Giuseppe Serra, Ben Werner, Florian Buettner
Many real-world applications require machine-learning models to be able to deal with non-stationary data distributions and thus learn autonomously over an extended period of time,…