Brief Review — Deep-Recursive Residual Network for Image Semantic Segmentation

Using Recursive Blocks for Semantic Segmentation

3 min readFeb 24, 2023

Deep-Recursive Residual Network for Image Semantic Segmentation,
Zhang JNCA’20, by Donghua University, and City University of Hong Kong,
2020 J. Neural Computing and Applications, Over 15 Citations (Sik-Ho Tsang @ Medium)
Semantic Segmentation
1.5. Semantic Segmentation / Scene Parsing / Instance Segmentation / Panoptic Segmentation
2014 … 2021 [PVT, PVTv1] [SETR] [Trans10K-v2, Trans2Seg] [Copy-Paste] 2022 [PVTv2] [YOLACT++]
==== My Other Paper Readings Are Also Over Here ====

As recursive block can improve performance without introducing new parameters, recursive block is utilized with the concatenation layer to combine the output maps of the recursive convolution layers with same resolution but different field-of-views.

Outline

Recursive Block Utilization
Results

1. Recursive Block Utilization

1.1. Recursive Block

Recursive block stacking three recursions with residual unit. If it is unfolded, this structure produces 8 paths for data to choose.

**Illustration of Applying Recursive Blocks**

Inspired by FPN, all output maps from recursive convolution layers are concatenated. That is to combine large field-of-view, semantically strong features with small field-of-view, semantically weak features via concatenation operation and the concatenated maps contain rich semantic information but with high channel dimension.
For the trade-off between computation and accuracy, the maps need to perform a 1×1 convolution layers to reduce channel dimension as well as merge all information.

1.2. Networks

Simplified FCN, and Simplified FCN with atrous convolution are used.
They are using VGG backbone. The fifth block which contains 3 convolution is replaced by the proposed recursive block.