Spectral Prompt Tuning: Unveiling Unseen Classes for Zero-Shot Semantic Segmentation
Proceedings of the AAAI Conference on Artificial Intelligence · 24.03.2024 · 38 (6) · 6369-6377
DOI: 10.1609/aaai.v38i6.28456 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 24.03.2024. Verfasst von Wenhao Xu und 6 weiteren Autor:innen. Die Arbeit wurde bisher 18-mal zitiert (Crossref).
Abstract (Originalsprache)
Recently, CLIP has found practical utility in the domain of pixel-level zero-shot segmentation tasks. The present landscape features two-stage methodologies beset by issues such as intricate pipelines and elevated computational costs. While current one-stage approaches alleviate these concerns and incorporate Visual Prompt Training (VPT) to uphold CLIP's generalization capacity, they still fall short in fully harnessing CLIP's potential for pixel-level unseen class demarcation and precise pixel predictions. To further stimulate CLIP's zero-shot dense prediction capability, we propose SPT-SEG, a one-stage approach that improves CLIP's adaptability from image to pixel. Specifically, we initially introduce Spectral Prompt Tuning (SPT), incorporating spectral prompts into the CLIP visual encoder's shallow layers to capture structural intricacies of images, thereby enhancing comprehension of unseen classes. Subsequently, we introduce the Spectral Guided Decoder (SGD), utilizing both high and low-frequency information to steer the network's spatial focus towards more prominent classification features, enabling precise pixel-level prediction outcomes. Through extensive experiments on two public datasets, we demonstrate the superiority of our method over state-of-the-art approaches, performing well across all classes and particularly excelling in handling unseen classes.
Zitieren
APA
Xu, W., Xu, R., Wang, C., Xu, S., Guo, L., Zhang, M., & Zhang, X. (2024). Spectral Prompt Tuning: Unveiling Unseen Classes for Zero-Shot Semantic Segmentation. Proceedings of the AAAI Conference on Artificial Intelligence, 38(6), 6369-6377. https://doi.org/10.1609/aaai.v38i6.28456
Vancouver
Xu W, Xu R, Wang C, Xu S, Guo L, Zhang M, et al. Spectral Prompt Tuning: Unveiling Unseen Classes for Zero-Shot Semantic Segmentation. Proceedings of the AAAI Conference on Artificial Intelligence. 2024;38(6):6369-6377. doi:10.1609/aaai.v38i6.28456
BibTeX
@article{Xu2024,
author = {Xu, Wenhao and Xu, Rongtao and Wang, Changwei and Xu, Shibiao and Guo, Li and Zhang, Man and Zhang, Xiaopeng},
title = {Spectral Prompt Tuning: Unveiling Unseen Classes for Zero-Shot Semantic Segmentation},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2024},
volume = {38},
number = {6},
pages = {6369--6377},
doi = {10.1609/aaai.v38i6.28456}
}
EUVIMED