Pre-training vision models for the classification of alerts from wide-field time-domain surveys
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_ | 1866917330752110592 |
|---|---|
| author | Rehemtulla, Nabeel Miller, Adam A. Walmsley, Mike Shah, Ved G. Laz, Theophile Jegou du Coughlin, Michael W. Sasli, Argyro Bloom, Joshua Fremling, Christoffer Graham, Matthew J. Groom, Steven L. Hale, David Mahabal, Ashish A. Perley, Daniel A. Purdum, Josiah Rusholme, Ben Sollerman, Jesper Kasliwal, Mansi M. |
| author_facet | Rehemtulla, Nabeel Miller, Adam A. Walmsley, Mike Shah, Ved G. Laz, Theophile Jegou du Coughlin, Michael W. Sasli, Argyro Bloom, Joshua Fremling, Christoffer Graham, Matthew J. Groom, Steven L. Hale, David Mahabal, Ashish A. Perley, Daniel A. Purdum, Josiah Rusholme, Ben Sollerman, Jesper Kasliwal, Mansi M. |
| contents | Modern wide-field time-domain surveys facilitate the study of transient, variable and moving phenomena by conducting image differencing and relaying alerts to their communities. Machine learning tools have been used on data from these surveys and their precursors for more than a decade, and convolutional neural networks (CNNs), which make predictions directly from input images, saw particularly broad adoption through the 2010s. Since then, continually rapid advances in computer vision have transformed the standard practices around using such models. It is now commonplace to use standardized architectures pre-trained on large corpora of everyday images (e.g., ImageNet). In contrast, time-domain astronomy studies still typically design custom CNN architectures and train them from scratch. Here, we explore the effects of adopting various pre-training regimens and standardized model architectures on the performance of alert classification. We find that the resulting models match or outperform a custom, specialized CNN like what is typically used for filtering alerts. Moreover, our results show that pre-training on galaxy images from Galaxy Zoo tends to yield better performance than pre-training on ImageNet or training from scratch. We observe that the design of standardized architectures are much better optimized than the custom CNN baseline, requiring significantly less time and memory for inference despite having more trainable parameters. On the eve of the Legacy Survey of Space and Time and other image-differencing surveys, these findings advocate for a paradigm shift in the creation of vision models for alerts, demonstrating that greater performance and efficiency, in time and in data, can be achieved by adopting the latest practices from the computer vision field. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_11957 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Pre-training vision models for the classification of alerts from wide-field time-domain surveys Rehemtulla, Nabeel Miller, Adam A. Walmsley, Mike Shah, Ved G. Laz, Theophile Jegou du Coughlin, Michael W. Sasli, Argyro Bloom, Joshua Fremling, Christoffer Graham, Matthew J. Groom, Steven L. Hale, David Mahabal, Ashish A. Perley, Daniel A. Purdum, Josiah Rusholme, Ben Sollerman, Jesper Kasliwal, Mansi M. Instrumentation and Methods for Astrophysics Computer Vision and Pattern Recognition Modern wide-field time-domain surveys facilitate the study of transient, variable and moving phenomena by conducting image differencing and relaying alerts to their communities. Machine learning tools have been used on data from these surveys and their precursors for more than a decade, and convolutional neural networks (CNNs), which make predictions directly from input images, saw particularly broad adoption through the 2010s. Since then, continually rapid advances in computer vision have transformed the standard practices around using such models. It is now commonplace to use standardized architectures pre-trained on large corpora of everyday images (e.g., ImageNet). In contrast, time-domain astronomy studies still typically design custom CNN architectures and train them from scratch. Here, we explore the effects of adopting various pre-training regimens and standardized model architectures on the performance of alert classification. We find that the resulting models match or outperform a custom, specialized CNN like what is typically used for filtering alerts. Moreover, our results show that pre-training on galaxy images from Galaxy Zoo tends to yield better performance than pre-training on ImageNet or training from scratch. We observe that the design of standardized architectures are much better optimized than the custom CNN baseline, requiring significantly less time and memory for inference despite having more trainable parameters. On the eve of the Legacy Survey of Space and Time and other image-differencing surveys, these findings advocate for a paradigm shift in the creation of vision models for alerts, demonstrating that greater performance and efficiency, in time and in data, can be achieved by adopting the latest practices from the computer vision field. |
| title | Pre-training vision models for the classification of alerts from wide-field time-domain surveys |
| topic | Instrumentation and Methods for Astrophysics Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2512.11957 |