EUVIMEDEUVIMED entdecken
Crossref

Prompt-and-Transfer: Dynamic Class-Aware Enhancement for Few-Shot Segmentation

Hanbo Bi, Yingchao Feng, Wenhui Diao, Peijin Wang, Yongqiang Mao, Kun Fu, Hongqi Wang, Xian Sun

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2025-01 · 47 (1) · 131-148

DOI: 10.1109/tpami.2024.3461779 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025-01. Verfasst von Hanbo Bi und 7 weiteren Autor:innen. Die Arbeit wurde bisher 38-mal zitiert (Crossref) und nennt 84 Literaturangaben. Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

For more efficient generalization to unseen domains (classes), most Few-shot Segmentation (FSS) would directly exploit pre-trained encoders and only fine-tune the decoder, especially in the current era of large models. However, such fixed feature encoders tend to be class-agnostic, inevitably activating objects that are irrelevant to the target class. In contrast, humans can effortlessly focus on specific objects in the line of sight. This paper mimics the visual perception pattern of human beings and proposes a novel and powerful prompt-driven scheme, called "Prompt and Transfer" (PAT), which constructs a dynamic class-aware prompting paradigm to tune the encoder for focusing on the interested object (target class) in the current task. Three key points are elaborated to enhance the prompting: 1) Cross-modal linguistic information is introduced to initialize prompts for each task. 2) Semantic Prompt Transfer (SPT) that precisely transfers the class-specific semantics within the images to prompts. 3) Part Mask Generator (PMG) that works in conjunction with SPT to adaptively generate different but complementary part prompts for different individuals. Surprisingly, PAT achieves competitive performance on 4 different tasks including standard FSS, Cross-domain FSS (e.g., CV, medical, and remote sensing domains), Weak-label FSS, and Zero-shot Segmentation, setting new state-of-the-arts on 11 benchmarks.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Bi, H., Feng, Y., Diao, W., Wang, P., Mao, Y., Fu, K., Wang, H., & Sun, X. (2025). Prompt-and-Transfer: Dynamic Class-Aware Enhancement for Few-Shot Segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 47(1), 131-148. https://doi.org/10.1109/tpami.2024.3461779

Vancouver

Bi H, Feng Y, Diao W, Wang P, Mao Y, Fu K, et al. Prompt-and-Transfer: Dynamic Class-Aware Enhancement for Few-Shot Segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2025;47(1):131-148. doi:10.1109/tpami.2024.3461779

BibTeX
@article{Bi2025,
  author = {Bi, Hanbo and Feng, Yingchao and Diao, Wenhui and Wang, Peijin and Mao, Yongqiang and Fu, Kun and Wang, Hongqi and Sun, Xian},
  title = {Prompt-and-Transfer: Dynamic Class-Aware Enhancement for Few-Shot Segmentation},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2025},
  volume = {47},
  number = {1},
  pages = {131--148},
  doi = {10.1109/tpami.2024.3461779}
}
Kostenlos starten →