# Learning Dynamic Routing for Semantic Segmentation

arXiv: https://arxiv.org/abs/2003.10401 · HTML: https://mlsanity.com/paper/2003.10401/

## Key facts

- Cited by 79 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Mar 2020.

## Built on by (most cited first, 30 of 79)

- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [Dynamic Neural Networks: A Survey](https://mlsanity.com/paper/2102.04906/) (2021)
- [GPT4Tools: Teaching Large Language Model to Use Tools via Self-instruction](https://mlsanity.com/paper/2305.18752/) (2023)
- [Rethinking Semantic Segmentation: A Prototype View](https://mlsanity.com/paper/2203.15102/) (2022)
- [Large-scale Unsupervised Semantic Segmentation](https://mlsanity.com/paper/2106.03149/) (2021)
- [Dynamic Slimmable Network](https://mlsanity.com/paper/2103.13258/) (2021)
- [Towards Accurate Image Coding: Improved Autoregressive Image Generation with Dynamic Vector Quantization](https://mlsanity.com/paper/2305.11718/) (2023)
- [Dynamic Multimodal Fusion](https://mlsanity.com/paper/2204.00102/) (2022)
- [DiNTS: Differentiable Neural Network Topology Search for 3D Medical Image Segmentation](https://mlsanity.com/paper/2103.15954/) (2021)
- [TAda! Temporally-Adaptive Convolutions for Video Understanding](https://mlsanity.com/paper/2110.06178/) (2021)
- [Fully Convolutional Networks for Panoptic Segmentation with Point-based Supervision](https://mlsanity.com/paper/2108.07682/) (2021)
- [Meta-Adapter: An Online Few-shot Learner for Vision-Language Model](https://mlsanity.com/paper/2311.03774/) (2023)
- [StructToken : Rethinking Semantic Segmentation with Structural Prior](https://mlsanity.com/paper/2203.12612/) (2022)
- [HRTransNet: HRFormer-Driven Two-Modality Salient Object Detection](https://mlsanity.com/paper/2301.03036/) (2023)
- [Resolution learning in deep convolutional networks using scale-space theory](https://mlsanity.com/paper/2106.03412/) (2021)
- [MicroNet: Improving Image Recognition with Extremely Low FLOPs](https://mlsanity.com/paper/2108.05894/) (2021)
- [DBQ-SSD: Dynamic Ball Query for Efficient 3D Object Detection](https://mlsanity.com/paper/2207.10909/) (2022)
- [Dynamic Tuning Towards Parameter and Inference Efficiency for ViT Adaptation](https://mlsanity.com/paper/2403.11808/) (2024)
- [Dynamic Spatial Sparsification for Efficient Vision Transformers and Convolutional Neural Networks](https://mlsanity.com/paper/2207.01580/) (2022)
- [Dynamic Grained Encoder for Vision Transformers](https://mlsanity.com/paper/2301.03831/) (2023)
- [Controllable Dynamic Multi-Task Architectures](https://mlsanity.com/paper/2203.14949/) (2022)
- [Continual Object Detection via Prototypical Task Correlation Guided Gating Mechanism](https://mlsanity.com/paper/2205.03055/) (2022)
- [Multi-Exit Semantic Segmentation Networks](https://mlsanity.com/paper/2106.03527/) (2021)
- [LOGICSEG: Parsing Visual Semantics with Neural Logic Learning and Reasoning](https://mlsanity.com/paper/2309.13556/) (2023)
- [Incremental Few-Shot Semantic Segmentation via Embedding Adaptive-Update and Hyper-class Representation](https://mlsanity.com/paper/2207.12964/) (2022)
- [Semantically Meaningful Class Prototype Learning for One-Shot Image Semantic Segmentation](https://mlsanity.com/paper/2102.10935/) (2021)
- [Semantic Segmentation by Early Region Proxy](https://mlsanity.com/paper/2203.14043/) (2022)
- [Computation-efficient Deep Learning for Computer Vision: A Survey](https://mlsanity.com/paper/2308.13998/) (2023)
- [Improving Video Instance Segmentation via Temporal Pyramid Routing](https://mlsanity.com/paper/2107.13155/) (2021)
- [DSE-GAN: Dynamic Semantic Evolution Generative Adversarial Network for Text-to-Image Generation](https://mlsanity.com/paper/2209.01339/) (2022)

## Abstract (arXiv)

Recently, numerous handcrafted and searched networks have been applied for semantic segmentation. However, previous works intend to handle inputs with various scales in pre-defined static architectures, such as FCN, U-Net, and DeepLab series. This paper studies a conceptually new method to alleviate the scale variance in semantic representation, named dynamic routing. The proposed framework generates data-dependent routes, adapting to the scale distribution of each image. To this end, a differentiable gating function, called soft conditional gate, is proposed to select scale transform paths on the fly. In addition, the computational cost can be further reduced in an end-to-end manner by giving budget constraints to the gating function. We further relax the network level routing space to support multi-path propagations and skip-connections in each forward, bringing substantial network capacity. To demonstrate the superiority of the dynamic property, we compare with several static architectures, which can be modeled as special cases in the routing space. Extensive experiments are conducted on Cityscapes and PASCAL VOC 2012 to illustrate the effectiveness of the dynamic framework. Code is available at https://github.com/yanwei-li/DynamicRouting.