ZoomNeXt: A Unified Collaborative Pyramid Network for Camouflaged Object Detection
IEEE Transactions on Pattern Analysis and Machine Intelligence · 2024-12 · 46 (12) · 9205-9220
DOI: 10.1109/tpami.2024.3417329 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024-12. Verfasst von Youwei Pang und 4 weiteren Autor:innen. Die Arbeit wurde bisher 135-mal zitiert (Crossref) und nennt 103 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Dalian Science and Technology Innovation Foundation.
Abstract (Originalsprache)
Recent camouflaged object detection (COD) attempts to segment objects visually blended into their surroundings, which is extremely complex and difficult in real-world scenarios. Apart from the high intrinsic similarity between camouflaged objects and their background, objects are usually diverse in scale, fuzzy in appearance, and even severely occluded. To this end, we propose an effective unified collaborative pyramid network that mimics human behavior when observing vague images and videos, i.e., zooming in and out. Specifically, our approach employs the zooming strategy to learn discriminative mixed-scale semantics by the multi-head scale integration and rich granularity perception units, which are designed to fully explore imperceptible clues between candidate objects and background surroundings. The former's intrinsic multi-head aggregation provides more diverse visual patterns. The latter's routing mechanism can effectively propagate inter-frame differences in spatiotemporal scenarios and be adaptively deactivated and output all-zero results for static representations. They provide a solid foundation for realizing a unified architecture for static and dynamic COD. Moreover, considering the uncertainty and ambiguity derived from indistinguishable textures, we construct a simple yet effective regularization, uncertainty awareness loss, to encourage predictions with higher confidence in candidate regions. Our highly task-friendly framework consistently outperforms existing state-of-the-art methods in image and video COD benchmarks.
Förderung
- National Natural Science Foundation of China
- Dalian Science and Technology Innovation Foundation
Zitieren
APA
Pang, Y., Zhao, X., Xiang, T. Z., Zhang, L., & Lu, H. (2024). ZoomNeXt: A Unified Collaborative Pyramid Network for Camouflaged Object Detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 46(12), 9205-9220. https://doi.org/10.1109/tpami.2024.3417329
Vancouver
Pang Y, Zhao X, Xiang TZ, Zhang L, Lu H. ZoomNeXt: A Unified Collaborative Pyramid Network for Camouflaged Object Detection. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2024;46(12):9205-9220. doi:10.1109/tpami.2024.3417329
BibTeX
@article{Pang2024,
author = {Pang, Youwei and Zhao, Xiaoqi and Xiang, Tian-Zhu and Zhang, Lihe and Lu, Huchuan},
title = {ZoomNeXt: A Unified Collaborative Pyramid Network for Camouflaged Object Detection},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
year = {2024},
volume = {46},
number = {12},
pages = {9205--9220},
doi = {10.1109/tpami.2024.3417329}
}
EUVIMED