EUVIMEDEUVIMED entdecken
Crossref

Generalizable Fourier Augmentation for Unsupervised Video Object Segmentation

Huihui Song, Tiankang Su, Yuhui Zheng, Kaihua Zhang, Bo Liu, Dong Liu

Proceedings of the AAAI Conference on Artificial Intelligence · 24.03.2024 · 38 (5) · 4918-4924

DOI: 10.1609/aaai.v38i5.28295 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 24.03.2024. Verfasst von Huihui Song und 5 weiteren Autor:innen. Die Arbeit wurde bisher 11-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The performance of existing unsupervised video object segmentation methods typically suffers from severe performance degradation on test videos when tested in out-of-distribution scenarios. The primary reason is that the test data in real- world may not follow the independent and identically distribution (i.i.d.) assumption, leading to domain shift. In this paper, we propose a generalizable fourier augmentation method during training to improve the generalization ability of the model. To achieve this, we perform Fast Fourier Transform (FFT) over the intermediate spatial domain features in each layer to yield corresponding frequency representations, including amplitude components (encoding scene-aware styles such as texture, color, contrast of the scene) and phase components (encoding rich semantics). We produce a variety of style features via Gaussian sampling to augment the training data, thereby improving the generalization capability of the model. To further improve the cross-domain generalization performance of the model, we design a phase feature update strategy via exponential moving average using phase features from past frames in an online update manner, which could help the model to learn cross-domain-invariant features. Extensive experiments show that our proposed method achieves the state-of-the-art performance on popular benchmarks.

Zitieren

APA

Song, H., Su, T., Zheng, Y., Zhang, K., Liu, B., & Liu, D. (2024). Generalizable Fourier Augmentation for Unsupervised Video Object Segmentation. Proceedings of the AAAI Conference on Artificial Intelligence, 38(5), 4918-4924. https://doi.org/10.1609/aaai.v38i5.28295

Vancouver

Song H, Su T, Zheng Y, Zhang K, Liu B, Liu D. Generalizable Fourier Augmentation for Unsupervised Video Object Segmentation. Proceedings of the AAAI Conference on Artificial Intelligence. 2024;38(5):4918-4924. doi:10.1609/aaai.v38i5.28295

BibTeX
@article{Song2024,
  author = {Song, Huihui and Su, Tiankang and Zheng, Yuhui and Zhang, Kaihua and Liu, Bo and Liu, Dong},
  title = {Generalizable Fourier Augmentation for Unsupervised Video Object Segmentation},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2024},
  volume = {38},
  number = {5},
  pages = {4918--4924},
  doi = {10.1609/aaai.v38i5.28295}
}
Kostenlos starten →