AUEB NLP Group at ImageCLEFmed Caption 2020

• This article concerns the participation of AUEB’s NLP Group in the ImageCLEFmed Caption task of 2020. The goal of the task was to identify medical terms that best describe each image, in order to accelerate and improve the interpretation of medical images by experts and systems. The systems we implemented extend our previous work [7,8,9] on models that employ CNN image encoders combined with an image retrieval method or a feed-forward neural network. Our systems were ranked 1st, 2nd and 6th.

Ämnesord

NATURVETENSKAP  -- Data- och informationsvetenskap -- Datavetenskap (hsv//swe)

NATURAL SCIENCES  -- Computer and Information Sciences -- Computer Sciences (hsv//eng)

Nyckelord

Medical Images

Concept Detection

Image Retrieval

Image Captioning

Multi-label Classification

Multimodal

Ensemble

Convolutional Neural Network (CNN)

Machine Learning

Deep Learning

Computer and Systems Sciences

data- och systemvetenskap

Publikations- och innehållstyp

ref (ämneskategori)

kon (ämneskategori)