Learning to Detect Salient Object With Multi-Source Weak Supervision

High-cost pixel-level annotations makes it appealing to train saliency detection models with weak supervision. However, a single weak supervision source hardly contain enough information to train a well-performing model. To this end, we introduce a unified two-stage framework to learn from category...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on pattern analysis and machine intelligence. - 1979. - 44(2022), 7 vom: 04. Juli, Seite 3577-3589
1. Verfasser: Zhang, Hongshuang (VerfasserIn)
Weitere Verfasser: Zeng, Yu, Lu, Huchuan, Zhang, Lihe, Li, Jianhua, Qi, Jinqing
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2022
Zugriff auf das übergeordnete Werk:IEEE transactions on pattern analysis and machine intelligence
Schlagworte:Journal Article
Beschreibung
Zusammenfassung:High-cost pixel-level annotations makes it appealing to train saliency detection models with weak supervision. However, a single weak supervision source hardly contain enough information to train a well-performing model. To this end, we introduce a unified two-stage framework to learn from category labels, captions, web images and unlabeled images. In the first stage, we design a classification network (CNet) and a caption generation network (PNet), which learn to predict object categories and generate captions, respectively, meanwhile highlights the potential foreground regions. We present an attention transfer loss to transmit supervisions between two tasks and an attention coherence loss to encourage the networks to detect generally salient regions instead of task-specific regions. In the second stage, we create two complementary training datasets using CNet and PNet, i.e., natural image dataset with noisy labels for adapting saliency prediction network (SNet) to natural image input, and synthesized image dataset by pasting objects on background images for providing SNet with accurate ground-truth. During the testing phases, we only need SNet to predict saliency maps. Experiments indicate the performance of our method compares favorably against unsupervised, weakly supervised methods and even some supervised methods
Beschreibung:Date Revised 07.06.2022
published: Print-Electronic
Citation Status PubMed-not-MEDLINE
ISSN:1939-3539
DOI:10.1109/TPAMI.2021.3059783