TopicFM: Robust and Interpretable Topic-Assisted Feature Matching
Khang Truong Giang, Soohwan Song, Sungho Jo
Abstract
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.
BibTeX
@article{Truong Giang_Song_Jo_2023, title={TopicFM: Robust and Interpretable Topic-Assisted Feature Matching}, volume={37}, url={https://ojs.aaai.org/index.php/AAAI/article/view/25341}, DOI={10.1609/aaai.v37i2.25341}, abstractNote={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.}, number={2}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Truong Giang, Khang and Song, Soohwan and Jo, Sungho}, year={2023}, month={Jun.}, pages={2447-2455} }