1 code implementation • 21 Apr 2022 • Benedikt Boecking, Naoto Usuyama, Shruthi Bannur, Daniel C. Castro, Anton Schwaighofer, Stephanie Hyland, Maria Wetscherek, Tristan Naumann, Aditya Nori, Javier Alvarez-Valle, Hoifung Poon, Ozan Oktay
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.
1 code implementation • NeurIPS 2021 • Salva Rühling Cachay, Benedikt Boecking, Artur Dubrawski
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
1 code implementation • ICLR 2021 • Benedikt Boecking, Willie Neiswanger, Eric Xing, Artur Dubrawski
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.
1 code implementation • 23 Mar 2022 • Benedikt Boecking, Vincent Jeanselme, Artur Dubrawski
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.
1 code implementation • 22 Mar 2022 • Benedikt Boecking, Nicholas Roberts, Willie Neiswanger, Stefano Ermon, Frederic Sala, Artur Dubrawski
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.
no code implementations • 3 Dec 2017 • Kyle Hundman, Thamme Gowda, Mayank Kejriwal, Benedikt Boecking
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.
no code implementations • 16 Dec 2019 • Benedikt Boecking, Artur Dubrawski
We propose to improve modeling of latent class variables in the programmatic creation of labeled datasets by incorporating pairwise feedback into the process.
1 code implementation • 19 Jun 2019 • Maria De-Arteaga, Benedikt Boecking
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
no code implementations • 18 Jun 2021 • Salva Rühling Cachay, Benedikt Boecking, Artur Dubrawski
Data programming (DP) has proven to be an attractive alternative to costly hand-labeling of data.
no code implementations • 29 Sep 2021 • Mononito Goswami, Chufan Gao, Benedikt Boecking, Saswati Ray, Artur Dubrawski
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.
no code implementations • 9 Jan 2022 • Mononito Goswami, Benedikt Boecking, Artur Dubrawski
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.
no code implementations • CVPR 2023 • Shruthi Bannur, Stephanie Hyland, Qianchu Liu, Fernando Pérez-García, Maximilian Ilse, Daniel C. Castro, Benedikt Boecking, Harshita Sharma, Kenza Bouzid, Anja Thieme, Anton Schwaighofer, Maria Wetscherek, Matthew P. Lungren, Aditya Nori, Javier Alvarez-Valle, Ozan Oktay
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.