Featured papers

Research shows how AI models can help, potentially making environmental monitoring faster and cheaper.

We propose LMV-Net, a longitudinal multi-view model that combines explicit longitudinal alignment with analysis of CC and MLO mammograms.

We propose the FC-DLIF model, which offers a non-invasive alternative that is flexible to temporal shifts and different scan durations

We introduce SuperCM, a differentiable clustering module that uses a model's few labeled examples to guide how it groups all of its data.

We use gradient-based importance scores to reduce input features for deep-learning-based seasonal sea ice forecasting.

We propose a tied prototype model that improves few-shot medical segmentation via probabilistic modeling.

New study shows how deep learning can achieve human-level performance in estimating uncertainty when classifying foraminifera.

We propose ConBias, a bias diagnosis and debiasing pipeline for visual datasets.

ViTs partition images into square patches to extract tokenized features. But is this necessarily an optimal way of partitioning images?