Explicit Visual Prompting for Universal Foreground Segmentations
IEEE Transactions on Pattern Analysis and Machine Intelligence · 2026-02 · 48 (2) · 1762-1777
DOI: 10.1109/tpami.2025.3619490 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2026-02. Verfasst von Weihuang Liu und 3 weiteren Autor:innen. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 119 Literaturangaben. Gefördert von: Universidade de Macau, Science and Technology Development Fund, Guangdong Provincial Regional Joint Fund - Young Scientists Fund.
Abstract (Originalsprache)
Foreground segmentation is a fundamental problem in computer vision, which includes salient object detection, forgery detection, defocus blur detection, shadow detection, and camouflage object detection. Previous works have typically relied on domain-specific solutions to address accuracy and robustness issues in those applications. In this paper, we present a unified framework for a number of foreground segmentation tasks without any task-specific designs. We take inspiration from the widely-used pre-training and then prompt tuning protocols in NLP and propose a new visual prompting model, named Explicit Visual Prompting (EVP). Different from the previous visual prompting which is typically a dataset-level implicit embedding, our key insight is to enforce the tunable parameters focusing on the explicit visual content from each individual image, i.e., the features from frozen patch embeddings and high-frequency components. Our method freezes a pre-trained model and then learns task-specific knowledge using a few extra parameters. Despite introducing only a small number of tunable parameters, EVP achieves superior performance than full fine-tuning and other parameter-efficient fine-tuning methods. Experiments in fourteen datasets across five tasks show the proposed method outperforms other task-specific methods while being considerably simple. The proposed method demonstrates the scalability in different architectures, pre-trained weights, and tasks.
Förderung
- Universidade de Macau
- Science and Technology Development Fund
- Guangdong Provincial Regional Joint Fund - Young Scientists Fund
Zitieren
APA
Liu, W., Shen, X., Pun, C. M., & Cun, X. (2026). Explicit Visual Prompting for Universal Foreground Segmentations. IEEE Transactions on Pattern Analysis and Machine Intelligence, 48(2), 1762-1777. https://doi.org/10.1109/tpami.2025.3619490
Vancouver
Liu W, Shen X, Pun CM, Cun X. Explicit Visual Prompting for Universal Foreground Segmentations. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2026;48(2):1762-1777. doi:10.1109/tpami.2025.3619490
BibTeX
@article{Liu2026,
author = {Liu, Weihuang and Shen, Xi and Pun, Chi-Man and Cun, Xiaodong},
title = {Explicit Visual Prompting for Universal Foreground Segmentations},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
year = {2026},
volume = {48},
number = {2},
pages = {1762--1777},
doi = {10.1109/tpami.2025.3619490}
}
EUVIMED