Haphazard Inputs as Images in Online Learning
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915226503348224 |
|---|---|
| author | Agarwal, Rohit Dessai, Aryan Sekh, Arif Ahmed Agarwal, Krishna Horsch, Alexander Prasad, Dilip K. |
| author_facet | Agarwal, Rohit Dessai, Aryan Sekh, Arif Ahmed Agarwal, Krishna Horsch, Alexander Prasad, Dilip K. |
| contents | The field of varying feature space in online learning settings, also known as haphazard inputs, is very prominent nowadays due to its applicability in various fields. However, the current solutions to haphazard inputs are model-dependent and cannot benefit from the existing advanced deep-learning methods, which necessitate inputs of fixed dimensions. Therefore, we propose to transform the varying feature space in an online learning setting to a fixed-dimension image representation on the fly. This simple yet novel approach is model-agnostic, allowing any vision-based models to be applicable for haphazard inputs, as demonstrated using ResNet and ViT. The image representation handles the inconsistent input data seamlessly, making our proposed approach scalable and robust. We show the efficacy of our method on four publicly available datasets. The code is available at https://github.com/Rohit102497/HaphazardInputsAsImages. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_02912 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Haphazard Inputs as Images in Online Learning Agarwal, Rohit Dessai, Aryan Sekh, Arif Ahmed Agarwal, Krishna Horsch, Alexander Prasad, Dilip K. Computer Vision and Pattern Recognition Artificial Intelligence Emerging Technologies Machine Learning The field of varying feature space in online learning settings, also known as haphazard inputs, is very prominent nowadays due to its applicability in various fields. However, the current solutions to haphazard inputs are model-dependent and cannot benefit from the existing advanced deep-learning methods, which necessitate inputs of fixed dimensions. Therefore, we propose to transform the varying feature space in an online learning setting to a fixed-dimension image representation on the fly. This simple yet novel approach is model-agnostic, allowing any vision-based models to be applicable for haphazard inputs, as demonstrated using ResNet and ViT. The image representation handles the inconsistent input data seamlessly, making our proposed approach scalable and robust. We show the efficacy of our method on four publicly available datasets. The code is available at https://github.com/Rohit102497/HaphazardInputsAsImages. |
| title | Haphazard Inputs as Images in Online Learning |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Emerging Technologies Machine Learning |
| url | https://arxiv.org/abs/2504.02912 |