# Mixed Link Networks

arXiv: https://arxiv.org/abs/1802.01808 · HTML: https://mlsanity.com/paper/1802.01808/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Feb 2018.

## Built on by (most cited first, 10 of 10)

- [SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers](https://mlsanity.com/paper/2105.15203/) (2021)
- [Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions](https://mlsanity.com/paper/2102.12122/) (2021)
- [Polyp-PVT: Polyp Segmentation with Pyramid Vision Transformers](https://mlsanity.com/paper/2108.06932/) (2021)
- [RegNet: Self-Regulated Network for Image Classification](https://mlsanity.com/paper/2101.00590/) (2021)
- [Augmenting Deep Classifiers with Polynomial Neural Networks](https://mlsanity.com/paper/2104.07916/) (2021)
- [Encoding Enhanced Complex CNN for Accurate and Highly Accelerated MRI](https://mlsanity.com/paper/2306.11977/) (2023)
- [AFINet: Attentive Feature Integration Networks for Image Classification](https://mlsanity.com/paper/2105.04354/) (2021)
- [Student Helping Teacher: Teacher Evolution via Self-Knowledge Distillation](https://mlsanity.com/paper/2110.00329/) (2021)
- [Deep Networks for Image and Video Super-Resolution](https://mlsanity.com/paper/2201.11996/) (2022)
- [Image Superresolution using Scale-Recurrent Dense Network](https://mlsanity.com/paper/2201.11998/) (2022)

## Abstract (arXiv)

Basing on the analysis by revealing the equivalence of modern networks, we find that both ResNet and DenseNet are essentially derived from the same "dense topology", yet they only differ in the form of connection -- addition (dubbed "inner link") vs. concatenation (dubbed "outer link"). However, both two forms of connections have the superiority and insufficiency. To combine their advantages and avoid certain limitations on representation learning, we present a highly efficient and modularized Mixed Link Network (MixNet) which is equipped with flexible inner link and outer link modules. Consequently, ResNet, DenseNet and Dual Path Network (DPN) can be regarded as a special case of MixNet, respectively. Furthermore, we demonstrate that MixNets can achieve superior efficiency in parameter over the state-of-the-art architectures on many competitive datasets like CIFAR-10/100, SVHN and ImageNet.