73 citations · 305 across the 55 of their papers we have counts for
7 papers · 1 filter
Sample-Specific Debiasing for Better Image-Text Models
Peiqi Wang, Yingcheng Liu, Ching-Yun Ko +4
Self-supervised representation learning on image-text data facilitates crucial medical applications, such as image classification, visual grounding, and cross-modal retrieval. One…
Less is More: Rethinking Few-Shot Learning and Recurrent Neural Nets
Deborah Pereg, Martin Villiger, Brett Bouma +1
The statistical supervised learning framework assumes an input-output set with a joint probability distribution that is reliably represented by the training dataset. The learner is…
Discretization Invariant Networks for Learning Maps between Neural Fields
Clinton J. Wang, Polina Golland
With the emergence of powerful representations of continuous data in the form of neural fields, there is a need for discretization invariant learning: an approach for learning maps…
Harmonization and the Worst Scanner Syndrome
Daniel Moyer, Polina Golland
We show that for a wide class of harmonization/domain-invariance schemes several undesirable properties are unavoidable. If a predictive machine is made invariant to a set of domai…
DEMI: Discriminative Estimator of Mutual Information
Ruizhi Liao, Daniel Moyer, Polina Golland +1
Estimating mutual information between continuous random variables is often intractable and extremely challenging for high-dimensional data. Recent progress has leveraged neural net…
PEP: Parameter Ensembling by Perturbation
Alireza Mehrtash, Purang Abolmaesumi, Polina Golland +3
Ensembling is now recognized as an effective approach for increasing the predictive performance and calibration of deep networks. We introduce a new approach, Parameter Ensembling…
Diversifying Sparsity Using Variational Determinantal Point Processes
Nematollah Kayhan Batmanghelich, Gerald Quon, Alex Kulesza +3
We propose a novel diverse feature selection method based on determinantal point processes (DPPs). Our model enables one to flexibly define diversity based on the covariance of fea…