Hundreds of image-based SOD methods have been proposed in the past decades [6,24–27,46]. Early methods are mainly based on the handcrafted low-level features as well as heuristic priors. Recently, deep convolutional neural networks have set new state-of-the-art on salient object detecti...
We can mention among others, for example, hierarchical CNNs [34] and VGG networks (very deep convolutional neural networks with over a dozen convolutional layers) [35], new and interesting applications in mechanical engineering [36]. The CNN introduced in [1] is a network based on real-...
Image super-resolution using very deep residual channel attention networks. In Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany, 8–14 September 2018; pp. 286–301. [Google Scholar] Ledig, C.; Theis, L.; Huszár, F.; Caballero, J.; Cunningham, A.; ...
Hence, we can classify fusion algorithms into four categories based on the development trend in recent years: multiscale-transform-based (MST-based) (Xiao et al., 2019; Xing et al., 2020; Zhu et al., 2019; Du et al., 2017; Li et al., 2020c; Tan et al., 2020), deep-learning...
Li, Y., Zhao, W., Pan, J.: Deformable patterned fabric defect detection with fisher criterion-based Deep Learning. IEEE Trans. Autom. Sci. Eng. 14(2), 1256–1264 (2017) Article Google Scholar Ren, R., Hung, T., Tan, K.C.: A generic deep-learning-based approach for automated ...
Prior-Guided Deep Interference Mitigation for FMCW Radars. IEEE Trans. Geosci. Remote Sens. 2022, 60, 1–16. [Google Scholar] [CrossRef] Mun, J.; Ha, S.; Lee, J. Automotive Radar Signal Interference Mitigation Using RNN with Self-Attention. In Proceedings of the ICASSP 2020—2020 IEEE ...
Adversarial examples are created when an attacker introduces subtle, carefully crafted perturbations to a correctly classified image, leading the CNNs to classify it incorrectly with high confidence. With the widespread adoption of deep learning technology, developing effective defenses against such ...