Revealing the Underlying Patterns: Investigating Dataset Similarity, Performance, and Generalization
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909056449380352 |
|---|---|
| author | Achara, Akshit Pandey, Ram Krishna |
| author_facet | Achara, Akshit Pandey, Ram Krishna |
| contents | Supervised deep learning models require significant amount of labeled data to achieve an acceptable performance on a specific task. However, when tested on unseen data, the models may not perform well. Therefore, the models need to be trained with additional and varying labeled data to improve the generalization. In this work, our goal is to understand the models, their performance and generalization. We establish image-image, dataset-dataset, and image-dataset distances to gain insights into the model's behavior. Our proposed distance metric when combined with model performance can help in selecting an appropriate model/architecture from a pool of candidate architectures. We have shown that the generalization of these models can be improved by only adding a small number of unseen images (say 1, 3 or 7) into the training set. Our proposed approach reduces training and annotation costs while providing an estimate of model performance on unseen data in dynamic environments. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2308_03580 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Revealing the Underlying Patterns: Investigating Dataset Similarity, Performance, and Generalization Achara, Akshit Pandey, Ram Krishna Computer Vision and Pattern Recognition Artificial Intelligence Supervised deep learning models require significant amount of labeled data to achieve an acceptable performance on a specific task. However, when tested on unseen data, the models may not perform well. Therefore, the models need to be trained with additional and varying labeled data to improve the generalization. In this work, our goal is to understand the models, their performance and generalization. We establish image-image, dataset-dataset, and image-dataset distances to gain insights into the model's behavior. Our proposed distance metric when combined with model performance can help in selecting an appropriate model/architecture from a pool of candidate architectures. We have shown that the generalization of these models can be improved by only adding a small number of unseen images (say 1, 3 or 7) into the training set. Our proposed approach reduces training and annotation costs while providing an estimate of model performance on unseen data in dynamic environments. |
| title | Revealing the Underlying Patterns: Investigating Dataset Similarity, Performance, and Generalization |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2308.03580 |