EUVIMEDEUVIMED entdecken
Crossref

Rapid Salient Object Detection With Difference Convolutional Neural Networks

Zhuo Su, Li Liu, Matthias Muller, Jiehua Zhang, Diana Wofk, Ming-Ming Cheng, Matti Pietikainen

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2025-10 · 47 (10) · 9061-9077

DOI: 10.1109/tpami.2025.3583968 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2025-10. Verfasst von Zhuo Su und 6 weiteren Autor:innen. Die Arbeit wurde bisher 22-mal zitiert (Crossref) und nennt 117 Literaturangaben. Gefördert von: National Key Research and Development Program of China, Academy of Finland, National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper addresses the challenge of deploying salient object detection (SOD) on resource-constrained devices with real-time performance. While recent advances in deep neural networks have improved SOD, existing top-leading models are computationally expensive. We propose an efficient network design that combines traditional wisdom on SOD and the representation power of modern CNNs. Like biologically-inspired classical SOD methods relying on computing contrast cues to determine saliency of image regions, our model leverages Pixel Difference Convolutions (PDCs) to encode the feature contrasts. Differently, PDCs are incorporated in a CNN architecture so that the valuable contrast cues are extracted from rich feature maps. For efficiency, we introduce a difference convolution reparameterization (DCR) strategy that embeds PDCs into standard convolutions, eliminating computation and parameters at inference. Additionally, we introduce SpatioTemporal Difference Convolution (STDC) for video SOD, enhancing the standard 3D convolution with spatiotemporal contrast capture. Our models, SDNet for image SOD and STDNet for video SOD, achieve significant improvements in efficiency-accuracy trade-offs. On a Jetson Orin device, our models with $< $< 1M parameters operate at 46 FPS and 150 FPS on streamed images and videos, surpassing the second-best lightweight models in our experiments by more than $2\times$2× and $3\times$3× in speed with superior accuracy.

Förderung

  • National Key Research and Development Program of China
  • Academy of Finland
  • National Natural Science Foundation of China

Zitieren

APA

Su, Z., Liu, L., Muller, M., Zhang, J., Wofk, D., Cheng, M. M., & Pietikainen, M. (2025). Rapid Salient Object Detection With Difference Convolutional Neural Networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 47(10), 9061-9077. https://doi.org/10.1109/tpami.2025.3583968

Vancouver

Su Z, Liu L, Muller M, Zhang J, Wofk D, Cheng MM, et al. Rapid Salient Object Detection With Difference Convolutional Neural Networks. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2025;47(10):9061-9077. doi:10.1109/tpami.2025.3583968

BibTeX
@article{Su2025,
  author = {Su, Zhuo and Liu, Li and Muller, Matthias and Zhang, Jiehua and Wofk, Diana and Cheng, Ming-Ming and Pietikainen, Matti},
  title = {Rapid Salient Object Detection With Difference Convolutional Neural Networks},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2025},
  volume = {47},
  number = {10},
  pages = {9061--9077},
  doi = {10.1109/tpami.2025.3583968}
}
Kostenlos starten →