Google is all you need: Semi-Supervised Transfer Learning Strategy For Light Multimodal Multi-Task Classification Model
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917883214299136 |
|---|---|
| author | Liu, Haixu Jiang, Penghao Tao, Zerui |
| author_facet | Liu, Haixu Jiang, Penghao Tao, Zerui |
| contents | As the volume of digital image data increases, the effectiveness of image classification intensifies. This study introduces a robust multi-label classification system designed to assign multiple labels to a single image, addressing the complexity of images that may be associated with multiple categories (ranging from 1 to 19, excluding 12). We propose a multi-modal classifier that merges advanced image recognition algorithms with Natural Language Processing (NLP) models, incorporating a fusion module to integrate these distinct modalities. The purpose of integrating textual data is to enhance the accuracy of label prediction by providing contextual understanding that visual analysis alone cannot fully capture. Our proposed classification model combines Convolutional Neural Networks (CNN) for image processing with NLP techniques for analyzing textual description (i.e., captions). This approach includes rigorous training and validation phases, with each model component verified and analyzed through ablation experiments. Preliminary results demonstrate the classifier's accuracy and efficiency, highlighting its potential as an automatic image-labeling system. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_01611 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Google is all you need: Semi-Supervised Transfer Learning Strategy For Light Multimodal Multi-Task Classification Model Liu, Haixu Jiang, Penghao Tao, Zerui Computer Vision and Pattern Recognition Artificial Intelligence As the volume of digital image data increases, the effectiveness of image classification intensifies. This study introduces a robust multi-label classification system designed to assign multiple labels to a single image, addressing the complexity of images that may be associated with multiple categories (ranging from 1 to 19, excluding 12). We propose a multi-modal classifier that merges advanced image recognition algorithms with Natural Language Processing (NLP) models, incorporating a fusion module to integrate these distinct modalities. The purpose of integrating textual data is to enhance the accuracy of label prediction by providing contextual understanding that visual analysis alone cannot fully capture. Our proposed classification model combines Convolutional Neural Networks (CNN) for image processing with NLP techniques for analyzing textual description (i.e., captions). This approach includes rigorous training and validation phases, with each model component verified and analyzed through ablation experiments. Preliminary results demonstrate the classifier's accuracy and efficiency, highlighting its potential as an automatic image-labeling system. |
| title | Google is all you need: Semi-Supervised Transfer Learning Strategy For Light Multimodal Multi-Task Classification Model |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2501.01611 |