Search Results for author: Jean-Benoit Delbrouck

Found 23 papers, 14 papers with code

QIAI at MEDIQA 2021: Multimodal Radiology Report Summarization

1 code implementation NAACL (BioNLP) 2021 Jean-Benoit Delbrouck, Cassie Zhang, Daniel Rubin

This paper describes the solution of the QIAI lab sent to the Radiology Report Summarization (RRS) challenge at MEDIQA 2021.

ViLLA: Fine-Grained Vision-Language Representation Learning from Real-World Data

1 code implementation22 Aug 2023 Maya Varma, Jean-Benoit Delbrouck, Sarah Hooper, Akshay Chaudhari, Curtis Langlotz

The first key contribution of this work is to demonstrate through systematic evaluations that as the pairwise complexity of the training dataset increases, standard VLMs struggle to learn region-attribute relationships, exhibiting performance degradations of up to 37% on retrieval tasks.

object-detection Representation Learning +2

RoentGen: Vision-Language Foundation Model for Chest X-ray Generation

no code implementations23 Nov 2022 Pierre Chambon, Christian Bluethgen, Jean-Benoit Delbrouck, Rogier van der Sluijs, Małgorzata Połacin, Juan Manuel Zambrano Chaves, Tanishq Mathew Abraham, Shivanshu Purohit, Curtis P. Langlotz, Akshay Chaudhari

We present evidence that the resulting model (RoentGen) is able to create visually convincing, diverse synthetic CXR images, and that the output can be controlled to a new extent by using free-form text prompts including radiology-specific language.

Data Augmentation

Toward expanding the scope of radiology report summarization to multiple anatomies and modalities

1 code implementation15 Nov 2022 Zhihong Chen, Maya Varma, Xiang Wan, Curtis Langlotz, Jean-Benoit Delbrouck

We then conduct extensive experiments to evaluate the performance of models both within and across modality-anatomy pairs in MIMIC-RRS.


Improving the Factual Correctness of Radiology Report Generation with Semantic Rewards

1 code implementation21 Oct 2022 Jean-Benoit Delbrouck, Pierre Chambon, Christian Bluethgen, Emily Tsai, Omar Almusa, Curtis P. Langlotz

To overcome this limitation, we propose a new method, the RadGraph reward, to further improve the factual completeness and correctness of generated radiology reports.

named-entity-recognition Named Entity Recognition +1

Domino: Discovering Systematic Errors with Cross-Modal Embeddings

2 code implementations ICLR 2022 Sabri Eyuboglu, Maya Varma, Khaled Saab, Jean-Benoit Delbrouck, Christopher Lee-Messer, Jared Dunnmon, James Zou, Christopher Ré

In this work, we address these challenges by first designing a principled evaluation framework that enables a quantitative comparison of SDMs across 1, 235 slice discovery settings in three input domains (natural images, medical images, and time-series data).

Representation Learning Time Series Analysis

Modulated Self-attention Convolutional Network for VQA

no code implementations8 Oct 2019 Jean-Benoit Delbrouck, Antoine Maiorca, Nathan Hubens, Stéphane Dupont

As new data-sets for real-world visual reasoning and compositional question answering are emerging, it might be needed to use the visual feature extraction as a end-to-end process during training.

Question Answering Visual Question Answering +1

Adversarial reconstruction for Multi-modal Machine Translation

no code implementations7 Oct 2019 Jean-Benoit Delbrouck, Stéphane Dupont

Even with the growing interest in problems at the intersection of Computer Vision and Natural Language, grounding (i. e. identifying) the components of a structured description in an image still remains a challenging task.

Machine Translation Translation

Object-oriented Targets for Visual Navigation using Rich Semantic Representations

no code implementations22 Nov 2018 Jean-Benoit Delbrouck, Stéphane Dupont

When searching for an object humans navigate through a scene using semantic information and spatial relationships.

Navigate Visual Navigation

UMONS Submission for WMT18 Multimodal Translation Task

1 code implementation15 Oct 2018 Jean-Benoit Delbrouck, Stéphane Dupont

This paper describes the UMONS solution for the Multimodal Machine Translation Task presented at the third conference on machine translation (WMT18).

Image Captioning Multimodal Machine Translation +1

Bringing back simplicity and lightliness into neural image captioning

no code implementations15 Oct 2018 Jean-Benoit Delbrouck, Stéphane Dupont

So far, the goal has been to maximize scores on automated metric and to do so, one has to come up with a plurality of new modules and techniques.

Image Captioning Machine Translation +1

Transformer for Emotion Recognition

1 code implementation3 May 2018 Jean-Benoit Delbrouck

This paper describes the UMONS solution for the OMG-Emotion Challenge.

Emotion Recognition

Modulating and attending the source image during encoding improves Multimodal Translation

1 code implementation9 Dec 2017 Jean-Benoit Delbrouck, Stéphane Dupont

We propose a new and fully end-to-end approach for multimodal translation where the source text encoder modulates the entire visual input processing using conditional batch normalization, in order to compute the most informative image features for our task.


Visually Grounded Word Embeddings and Richer Visual Features for Improving Multimodal Neural Machine Translation

no code implementations4 Jul 2017 Jean-Benoit Delbrouck, Stéphane Dupont, Omar Seddati

In Multimodal Neural Machine Translation (MNMT), a neural model generates a translated sentence that describes an image, given the image itself and one source descriptions in English.

Dense Captioning Machine Translation +4

Multimodal Compact Bilinear Pooling for Multimodal Neural Machine Translation

no code implementations23 Mar 2017 Jean-Benoit Delbrouck, Stephane Dupont

Recently, the effectiveness of the attention mechanism has also been explored for multimodal tasks, where it becomes possible to focus both on sentence parts and image regions.

Machine Translation Question Answering +2

Cannot find the paper you are looking for? You can Submit a new open access paper.