BridgeNet: Comprehensive and Effective Feature Interactions via Bridge Feature for Multi-Task Dense Predictions
Rattachement africain : cn, us. Niveau de preuve : code pays fourni par la source.
Le résumé fourni par la source
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.
Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.
Le contrôle bibliographique ouvert
DOI retrouvé dans Crossref DOI retrouvé ; titre concordant.
- Titre Crossref
- BridgeNet: Comprehensive and Effective Feature Interactions via Bridge Feature for Multi-Task Dense Predictions
- Date Crossref
- 01/05/2025
- Éditeur
- Institute of Electrical and Electronics Engineers (IEEE)
- Type
- journal-article
Ce recoupement confirme des métadonnées liées au DOI. Il ne confirme ni la méthode ni les conclusions de l’étude, et il ne compte pas comme une seconde source scientifique indépendante.
Où se fait cette recherche
-
Fudan University Academy for Engineering and Technology pays non établi dans la noticeUniversité ou école supérieure
-
Shanghai Artificial Intelligence Laboratory pays non établi dans la noticeStructure de recherche
-
Oracle (United States) pays non établi dans la noticeEntreprise
-
School of Information Science and Technology pays non établi dans la noticeUniversité ou école supérieure
-
Shanghai AI Laboratory pays non établi dans la noticeStructure de recherche
-
Redwood City pays non établi dans la noticeInstitution
Academy for Engineering and Technology — Fudan University, Shanghai Artificial Intelligence Laboratory et Oracle (United States), avec 3 autres affiliations.
Une affiliation ne permet pas de déduire la nationalité d’un auteur.