BridgeNet: Comprehensive and Effective Feature Interactions via Bridge Feature for Multi-Task Dense Predictions
IEEE Transactions on Pattern Analysis and Machine Intelligence · 2025-05 · 47 (5) · 3657-3672
DOI: 10.1109/tpami.2025.3535875 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025-05. Verfasst von Jingdong Zhang und 7 weiteren Autor:innen. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 57 Literaturangaben. Gefördert von: National Key Research and Development Program of China, Natural Science Foundation of Shanghai Municipality, Shanghai Science and Technology Commission Explorer Program Project.
Abstract (Originalsprache)
Multi-task dense prediction aims at handling multiple pixel-wise prediction tasks within a unified network simultaneously for visual scene understanding. However, cross-task feature interactions of current methods are still suffering from incomplete levels of representations, less discriminative semantics in feature participants, and inefficient pair-wise task interaction processes. To tackle these under-explored issues, we propose a novel BridgeNet framework, which extracts comprehensive and discriminative intermediate Bridge Features, and conducts interactions based on them. Specifically, a Task Pattern Propagation (TPP) module is first applied to ensure highly semantic task-specific feature participants are prepared for subsequent interactions, and a Bridge Feature Extractor (BFE) is specially designed to selectively integrate both high-level and low-level representations to generate the comprehensive bridge features. Then, instead of conducting heavy pair-wise cross-task interactions, a Task-Feature Refiner (TFR) is developed to efficiently take guidance from bridge features and form final task predictions. To the best of our knowledge, this is the first work considering the completeness and quality of feature participants in cross-task interactions. Extensive experiments are conducted on NYUD-v2, Cityscapes and PASCAL Context benchmarks, and the superior performance shows the proposed architecture is effective and powerful in promoting different dense prediction tasks simultaneously.
Förderung
- National Key Research and Development Program of China
- Natural Science Foundation of Shanghai Municipality
- Shanghai Science and Technology Commission Explorer Program Project
- Shanghai Municipal Science and Technology Major Project
Zitieren
APA
Zhang, J., Fan, J., Ye, P., Zhang, B., Ye, H., Li, B., Cai, Y., & Chen, T. (2025). BridgeNet: Comprehensive and Effective Feature Interactions via Bridge Feature for Multi-Task Dense Predictions. IEEE Transactions on Pattern Analysis and Machine Intelligence, 47(5), 3657-3672. https://doi.org/10.1109/tpami.2025.3535875
Vancouver
Zhang J, Fan J, Ye P, Zhang B, Ye H, Li B, et al. BridgeNet: Comprehensive and Effective Feature Interactions via Bridge Feature for Multi-Task Dense Predictions. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2025;47(5):3657-3672. doi:10.1109/tpami.2025.3535875
BibTeX
@article{Zhang2025,
author = {Zhang, Jingdong and Fan, Jiayuan and Ye, Peng and Zhang, Bo and Ye, Hancheng and Li, Baopu and Cai, Yancheng and Chen, Tao},
title = {BridgeNet: Comprehensive and Effective Feature Interactions via Bridge Feature for Multi-Task Dense Predictions},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
year = {2025},
volume = {47},
number = {5},
pages = {3657--3672},
doi = {10.1109/tpami.2025.3535875}
}
EUVIMED