Multi-Scale Residual Network (MSRN)

A Multi-Scale Residual Network (MSRN) is a Deep Residual Neural Network that contains multi-scale residual blocks.

• Context:
  • It was initially developed by Li et al. (2018).
• Example(s):
  • Li et al. (2018) propose MSRN architecture:

     .

• Counter-Example(s):
  • a He-Zhang-Ren-Sun Deep Residual Network,
  • a Spec-ResNet,
  • a Wide Residual Network (WRN).
• See: Residual Neural Network, Residual Neural Network, Convolutional Neural Network, Machine Learning, Deep Learning, Machine Vision.

---

---

References

2018

• (Li et al., 2018) ⇒ Juncheng Li, Faming Fang, Kangfu Mei, and Guixu Zhang. (2018). “Multi-scale Residual Network for Image Super-Resolution.” In: Proceedings of 15th European Conference in Computer Vision (ECCV 2018) - Part VIII.
  • QUOTE: In order to detect the image features at different scales, we propose multi-scale residual block (MSRB). Here we will provide a detailed description of this structure. As shown in Fig. 3, our MSRB contains two parts: multi-scale features fusion and local residual learning.

Figure 3: The structure of multi-scale residual block (MSRB).

---