TopicFM: Robust and Interpretable Topic-Assisted Feature Matching
Proceedings of the AAAI Conference on Artificial Intelligence · 26.06.2023 · 37 (2) · 2447-2455
DOI: 10.1609/aaai.v37i2.25341 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 26.06.2023. Verfasst von Khang Truong Giang und 2 weiteren Autor:innen. Die Arbeit wurde bisher 66-mal zitiert (Crossref).
Abstract (Originalsprache)
This study addresses an image-matching problem in challenging cases, such as large scene variations or textureless scenes. To gain robustness to such situations, most previous studies have attempted to encode the global contexts of a scene via graph neural networks or transformers. However, these contexts do not explicitly represent high-level contextual information, such as structural shapes or semantic instances; therefore, the encoded features are still not sufficiently discriminative in challenging scenes. We propose a novel image-matching method that applies a topic-modeling strategy to encode high-level contexts in images. The proposed method trains latent semantic instances called topics. It explicitly models an image as a multinomial distribution of topics, and then performs probabilistic feature matching. This approach improves the robustness of matching by focusing on the same semantic areas between the images. In addition, the inferred topics provide interpretability for matching the results, making our method explainable. Extensive experiments on outdoor and indoor datasets show that our method outperforms other state-of-the-art methods, particularly in challenging cases.
Zitieren
APA
Giang, K. T., Song, S., & Jo, S. (2023). TopicFM: Robust and Interpretable Topic-Assisted Feature Matching. Proceedings of the AAAI Conference on Artificial Intelligence, 37(2), 2447-2455. https://doi.org/10.1609/aaai.v37i2.25341
Vancouver
Giang KT, Song S, Jo S. TopicFM: Robust and Interpretable Topic-Assisted Feature Matching. Proceedings of the AAAI Conference on Artificial Intelligence. 2023;37(2):2447-2455. doi:10.1609/aaai.v37i2.25341
BibTeX
@article{Giang2023,
author = {Giang, Khang Truong and Song, Soohwan and Jo, Sungho},
title = {TopicFM: Robust and Interpretable Topic-Assisted Feature Matching},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2023},
volume = {37},
number = {2},
pages = {2447--2455},
doi = {10.1609/aaai.v37i2.25341}
}
EUVIMED