{"external_id":{"arxiv":["1711.06011"]},"author":[{"last_name":"Pai","first_name":"Gautam","full_name":"Pai, Gautam"},{"full_name":"Talmon, Ronen","first_name":"Ronen","last_name":"Talmon"},{"id":"58f3726e-7cba-11ef-ad8b-e6e8cb3904e6","last_name":"Bronstein","first_name":"Alexander","orcid":"0000-0001-9699-8730","full_name":"Bronstein, Alexander"},{"last_name":"Kimmel","first_name":"Ron","full_name":"Kimmel, Ron"}],"year":"2019","publication_identifier":{"isbn":["9781728119762"]},"month":"03","date_updated":"2024-12-05T14:51:53Z","scopus_import":"1","article_number":"8658791","type":"conference","date_created":"2024-10-08T13:09:16Z","arxiv":1,"oa":1,"doi":"10.1109/wacv.2019.00092","quality_controlled":"1","article_processing_charge":"No","abstract":[{"text":"This paper explores a fully unsupervised deep learning approach for computing distance-preserving maps that generate low-dimensional embeddings for a certain class of manifolds. We use the Siamese configuration to train a neural network to solve the problem of least squares multidimensional scaling for generating maps that approximately preserve geodesic distances. By training with only a few landmarks, we show a significantly improved local and nonlocal generalization of the isometric mapping as compared to analogous non-parametric counterparts. Importantly, the combination of a deep-learning framework with a multidimensional scaling objective enables a numerical analysis of network architectures to aid in understanding their representation power. This provides a geometric perspective to the generalizability of deep learning.","lang":"eng"}],"citation":{"ista":"Pai G, Talmon R, Bronstein AM, Kimmel R. 2019. DIMAL: Deep isometric manifold learning using sparse geodesic sampling. 2019 IEEE Winter Conference on Applications of Computer Vision (WACV). 19th IEEE Winter Conference on Applications of Computer Vision, 8658791.","short":"G. Pai, R. Talmon, A.M. Bronstein, R. Kimmel, in:, 2019 IEEE Winter Conference on Applications of Computer Vision (WACV), IEEE, 2019.","ama":"Pai G, Talmon R, Bronstein AM, Kimmel R. DIMAL: Deep isometric manifold learning using sparse geodesic sampling. In: <i>2019 IEEE Winter Conference on Applications of Computer Vision (WACV)</i>. IEEE; 2019. doi:<a href=\"https://doi.org/10.1109/wacv.2019.00092\">10.1109/wacv.2019.00092</a>","ieee":"G. Pai, R. Talmon, A. M. Bronstein, and R. Kimmel, “DIMAL: Deep isometric manifold learning using sparse geodesic sampling,” in <i>2019 IEEE Winter Conference on Applications of Computer Vision (WACV)</i>, Waikoloa, HI, United States, 2019.","mla":"Pai, Gautam, et al. “DIMAL: Deep Isometric Manifold Learning Using Sparse Geodesic Sampling.” <i>2019 IEEE Winter Conference on Applications of Computer Vision (WACV)</i>, 8658791, IEEE, 2019, doi:<a href=\"https://doi.org/10.1109/wacv.2019.00092\">10.1109/wacv.2019.00092</a>.","apa":"Pai, G., Talmon, R., Bronstein, A. M., &#38; Kimmel, R. (2019). DIMAL: Deep isometric manifold learning using sparse geodesic sampling. In <i>2019 IEEE Winter Conference on Applications of Computer Vision (WACV)</i>. Waikoloa, HI, United States: IEEE. <a href=\"https://doi.org/10.1109/wacv.2019.00092\">https://doi.org/10.1109/wacv.2019.00092</a>","chicago":"Pai, Gautam, Ronen Talmon, Alex M. Bronstein, and Ron Kimmel. “DIMAL: Deep Isometric Manifold Learning Using Sparse Geodesic Sampling.” In <i>2019 IEEE Winter Conference on Applications of Computer Vision (WACV)</i>. IEEE, 2019. <a href=\"https://doi.org/10.1109/wacv.2019.00092\">https://doi.org/10.1109/wacv.2019.00092</a>."},"_id":"18262","day":"07","main_file_link":[{"open_access":"1","url":"https://doi.org/10.48550/arXiv.1711.06011"}],"status":"public","conference":{"location":"Waikoloa, HI, United States","name":"19th IEEE Winter Conference on Applications of Computer Vision","end_date":"2019-01-11","start_date":"2019-01-07"},"publication_status":"published","language":[{"iso":"eng"}],"publication":"2019 IEEE Winter Conference on Applications of Computer Vision (WACV)","user_id":"3E5EF7F0-F248-11E8-B48F-1D18A9856A87","publisher":"IEEE","date_published":"2019-03-07T00:00:00Z","oa_version":"Preprint","title":"DIMAL: Deep isometric manifold learning using sparse geodesic sampling"}