paper-with-me

홈 › Papers

Automated Image Captioning with CNNs and Transformers

2024-12-13 · Joshua Adrian Cahyono, Jeremy Nathan Jusuf

This project aims to create an automated image captioning system that generates natural language descriptions for input images by integrating techniques from computer vision and natural language processing. We employ various different techniques, ranging from CNN-RNN to the more advanced transformer-based techniques. Training is carried out on image datasets paired with descriptive captions, and model performance will be evaluated using established metrics such as BLEU, METEOR, and CIDEr. The project will also involve experimentation with advanced attention mechanisms, comparisons of different architectural choices, and hyperparameter optimization to refine captioning accuracy and overall system effectiveness.

📄 PDF Abstract BibTeX arXiv:2412.10511

Code (1)

JeremyNathanJusuf/image-captioning 공식 구현 pytorch

Tasks

DescriptiveHyperparameter OptimizationImage Captioning

Methods 이 논문이 사용한 방법론

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Attention 설명 없음

Similar Papers 제목 키워드 기반

Is it Time to Replace CNNs with Transformers for Medical Images?

2021-08-20 · Christos Matsoukas, Johan Fredin Haslum, Magnus Söderberg, Kevin Smith

Convolutional Neural Networks (CNNs) have reigned for a decade as the de facto approach to automated medical image diagnosis. Recently, vision transformers (ViTs) have appeared as a competitive alternative to CNNs, yield…

Should we Replace CNNs with Transformers for Medical Images?

2021-09-29 · Christos Matsoukas, Johan Fredin Haslum, Moein Sorkhei, Magnus Soderberg 외

Convolutional Neural Networks (CNNs) have reigned for a decade as the de facto approach to automated medical image diagnosis, pushing the state-of-the-art in classification, detection and segmentation tasks. Recently, vi…

Segmentation

Pretrained ViTs Yield Versatile Representations For Medical Images

2023-03-13 · Christos Matsoukas, Johan Fredin Haslum, Moein Sorkhei, Magnus Söderberg 외

Convolutional Neural Networks (CNNs) have reigned for a decade as the de facto approach to automated medical image diagnosis, pushing the state-of-the-art in classification, detection and segmentation tasks. Over the las…

image-classificationImage ClassificationMedical Image Classification

Detecção da Psoríase Utilizando Visão Computacional: Uma Abordagem Comparativa Entre CNNs e Vision Transformers

2025-06-11 · Natanael Lucena, Fábio S. da Silva, Ricardo Rios

This paper presents a comparison of the performance of Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs) in the task of multi-classifying images containing lesions of psoriasis and diseases similar to i…

image-classificationImage ClassificationMedical Image Classification

Transformers in Medicine: Improving Vision-Language Alignment for Medical Image Captioning

2025-10-29 · Yogesh Thakku Suresh, Vishwajeet Shivaji Hogale, Luca-Alexandru Zamfira, Anandavardhana Hegde arxiv

We present a transformer-based multimodal framework for generating clinically relevant captions for MRI scans. Our system combines a DEiT-Small vision transformer as an image encoder, MediCareBERT for caption embedding, …

Image Captioning