Data Augmentation via Latent Diffusion for Saliency Prediction
Published in Proceedings of the European Conference on Computer Vision, 2024
We propose a novel data augmentation method for deep saliency prediction that edits natural images while preserving the complexity and variability of real-world scenes.
Recommended citation: Bahar Aydemir, Deblina Bhattacharjee, Tong Zhang, Mathieu Salzmann, Sabine Süsstrunk. (2024). "Data Augmentation via Latent Diffusion for Saliency Prediction." European Conference on Computer Vision (ECCV).
Download Paper | Download Slides