Active Learning for Multi-class Image Classification
Fuente:
arXiv
Enregistré dans:
| Auteur principal: | |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866908359723057152 |
|---|---|
| author | Vo, Thien Nhan |
| author_facet | Vo, Thien Nhan |
| contents | A principle bottleneck in image classification is the large number of training examples needed to train a classifier. Using active learning, we can reduce the number of training examples to teach a CNN classifier by strategically selecting examples. Assigning values to image examples using different uncertainty metrics allows the model to identify and select high-value examples in a smaller training set size. We demonstrate results for digit recognition and fruit classification on the MNIST and Fruits360 data sets. We formally compare results for four different uncertainty metrics. Finally, we observe active learning is also effective on simpler (binary) classification tasks, but marked improvement from random sampling is more evident on more difficult tasks. We show active learning is a viable algorithm for image classification problems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_06825 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Active Learning for Multi-class Image Classification Vo, Thien Nhan Computer Vision and Pattern Recognition Machine Learning A principle bottleneck in image classification is the large number of training examples needed to train a classifier. Using active learning, we can reduce the number of training examples to teach a CNN classifier by strategically selecting examples. Assigning values to image examples using different uncertainty metrics allows the model to identify and select high-value examples in a smaller training set size. We demonstrate results for digit recognition and fruit classification on the MNIST and Fruits360 data sets. We formally compare results for four different uncertainty metrics. Finally, we observe active learning is also effective on simpler (binary) classification tasks, but marked improvement from random sampling is more evident on more difficult tasks. We show active learning is a viable algorithm for image classification problems. |
| title | Active Learning for Multi-class Image Classification |
| topic | Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2505.06825 |