Morphological classification of eclipsing binary stars using computer vision methods
This work addresses morphological classification for astronomers using large-scale surveys, but it is incremental as it adapts existing computer vision models to a new domain with mixed results.
The authors tackled the problem of classifying eclipsing binary stars by applying computer vision methods to light curves, achieving high accuracy (>96% on validation and up to 100% on observational data) for binary classification but poor performance for automated spot detection.
We present an application of computer vision methods to classify the light curves of eclipsing binaries (EB). We have used pre-trained models based on convolutional neural networks ($\textit{ResNet50}$) and vision transformers ($\textit{vit\_base\_patch16\_224}$), which were fine-tuned on images created from synthetic datasets. To improve model generalisation and reduce overfitting, we developed a novel image representation by transforming phase-folded light curves into polar coordinates combined with hexbin visualisation. Our hierarchical approach in the first stage classifies systems into detached and overcontact types, and in the second stage identifies the presence or absence of spots. The binary classification models achieved high accuracy ($>96\%$) on validation data across multiple passbands (Gaia~$G$, $I$, and $TESS$) and demonstrated strong performance ($>94\%$, up to $100\%$ for $TESS$) when tested on extensive observational data from the OGLE, DEBCat, and WUMaCat catalogues. While the primary binary classification was highly successful, the secondary task of automated spot detection performed poorly, revealing a significant limitation of our models for identifying subtle photometric features. This study highlights the potential of computer vision for EB morphological classification in large-scale surveys, but underscores the need for further research into robust, automated spot detection.