EUVIMEDEUVIMED entdecken
Crossref

Divide-and-Conquer: Confluent Triple-Flow Network for RGB-T Salient Object Detection

Hao Tang, Zechao Li, Dong Zhang, Shengfeng He, Jinhui Tang

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2025-03 · 47 (3) · 1958-1974

DOI: 10.1109/tpami.2024.3511621 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025-03. Verfasst von Hao Tang und 4 weiteren Autor:innen. Die Arbeit wurde bisher 277-mal zitiert (Crossref) und nennt 81 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Basic Research Program of Jiangsu Province, Guangdong Natural Science Funds for Distinguished Young Scholars.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

RGB-Thermal Salient Object Detection (RGB-T SOD) aims to pinpoint prominent objects within aligned pairs of visible and thermal infrared images. A key challenge lies in bridging the inherent disparities between RGB and Thermal modalities for effective saliency map prediction. Traditional encoder-decoder architectures, while designed for cross-modality feature interactions, may not have adequately considered the robustness against noise originating from defective modalities, thereby leading to suboptimal performance in complex scenarios. Inspired by hierarchical human visual systems, we propose the ConTriNet, a robust Confluent Triple-Flow Network employing a "Divide-and-Conquer" strategy. This framework utilizes a unified encoder with specialized decoders, each addressing different subtasks of exploring modality-specific and modality-complementary information for RGB-T SOD, thereby enhancing the final saliency map prediction. Specifically, ConTriNet comprises three flows: two modality-specific flows explore cues from RGB and Thermal modalities, and a third modality-complementary flow integrates cues from both modalities. ConTriNet presents several notable advantages. It incorporates a Modality-induced Feature Modulator (MFM) in the modality-shared union encoder to minimize inter-modality discrepancies and mitigate the impact of defective samples. Additionally, a foundational Residual Atrous Spatial Pyramid Module (RASPM) in the separated flows enlarges the receptive field, allowing for the capture of multi-scale contextual information. Furthermore, a Modality-aware Dynamic Aggregation Module (MDAM) in the modality-complementary flow dynamically aggregates saliency-related cues from both modality-specific flows. Leveraging the proposed parallel triple-flow framework, we further refine saliency maps derived from different flows through a flow-cooperative fusion strategy, yielding a high-quality, full-resolution saliency map for the final prediction. To evaluate the robustness and stability of our approach, we collect a comprehensive RGB-T SOD benchmark, VT-IMAG, covering various real-world challenging scenarios. Extensive experiments on public benchmarks and our VT-IMAG dataset demonstrate that ConTriNet consistently outperforms state-of-the-art competitors in both common and challenging scenarios, even when dealing with incomplete modality data. The code and VT-IMAG will be available at: https://cser-tang-hao.github.io/contrinet.html.

Förderung

  • National Natural Science Foundation of China
  • Basic Research Program of Jiangsu Province
  • Guangdong Natural Science Funds for Distinguished Young Scholars
  • AI Singapore Programme
  • National Research Foundation Singapore
  • Lee Kong Chian Fellowships

Zitieren

APA

Tang, H., Li, Z., Zhang, D., He, S., & Tang, J. (2025). Divide-and-Conquer: Confluent Triple-Flow Network for RGB-T Salient Object Detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 47(3), 1958-1974. https://doi.org/10.1109/tpami.2024.3511621

Vancouver

Tang H, Li Z, Zhang D, He S, Tang J. Divide-and-Conquer: Confluent Triple-Flow Network for RGB-T Salient Object Detection. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2025;47(3):1958-1974. doi:10.1109/tpami.2024.3511621

BibTeX
@article{Tang2025,
  author = {Tang, Hao and Li, Zechao and Zhang, Dong and He, Shengfeng and Tang, Jinhui},
  title = {Divide-and-Conquer: Confluent Triple-Flow Network for RGB-T Salient Object Detection},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2025},
  volume = {47},
  number = {3},
  pages = {1958--1974},
  doi = {10.1109/tpami.2024.3511621}
}
Kostenlos starten →