Search Results for author:
Found 12 papers, 6 papers with code
Making the Most of Text Semantics to Improve Biomedical Vision--Language Processing
We release a new dataset with locally-aligned phrase grounding annotations by radiologists to facilitate the study of complex semantic modelling in biomedical vision--language processing.
End-to-End Weak Supervision
Aggregating multiple sources of weak supervision (WS) can ease the data-labeling bottleneck prevalent in many machine learning applications, by replacing the tedious manual collection of ground truth labels.
Ranked #1 on
Classification
on BiasBios
Interactive Weak Supervision: Learning Useful Heuristics for Data Labeling
Our experiments demonstrate that only a small number of feedback iterations are needed to train models that achieve highly competitive test set performance without access to ground truth training labels.
Constrained Clustering and Multiple Kernel Learning without Pairwise Constraint Relaxation
However, the common practice of relaxing discrete constraints to a continuous domain to ease optimization when learning kernels or metrics can harm generalization, as information which only encodes linkage is transformed to informing distances.
Generative Modeling Helps Weak Supervision (and Vice Versa)
The model outperforms baseline weak supervision label models on a number of multiclass image classification datasets, improves the quality of generated images, and further improves end-model performance through data augmentation with synthetic samples.
Always Lurking: Understanding and Mitigating Bias in Online Human Trafficking Detection
Web-based human trafficking activity has increased in recent years but it remains sparsely dispersed among escort advertisements and difficult to identify due to its often-latent nature.
Pairwise Feedback for Data Programming
We propose to improve modeling of latent class variables in the programmatic creation of labeled datasets by incorporating pairwise feedback into the process.
Killings of social leaders in the Colombian post-conflict: Data analysis for investigative journalism
After the peace agreement of 2016 with FARC, the killings of social leaders have emerged as an important post-conflict challenge for Colombia.
Applications Computers and Society
Dependency Structure Misspecification in Multi-Source Weak Supervision Models
Data programming (DP) has proven to be an attractive alternative to costly hand-labeling of data.
ACTIVE REFINEMENT OF WEAKLY SUPERVISED MODELS
In domains such as clinical research, where data collection and its careful characterization is particularly expensive and tedious, this reliance on pointillisticaly labeled data is one of the biggest roadblocks to the adoption of modern data-hungry ML algorithms.
Weak Supervision for Affordable Modeling of Electrocardiogram Data
We explore the use of multiple weak supervision sources to learn diagnostic models of abnormal heartbeats via human designed heuristics, without using ground truth labels on individual data points.
Learning to Exploit Temporal Structure for Biomedical Vision-Language Processing
Prior work in biomedical VLP has mostly relied on the alignment of single image and report pairs even though clinical notes commonly refer to prior images.
