# Dual Path Networks

arXiv: https://arxiv.org/abs/1707.01629 · HTML: https://mlsanity.com/paper/1707.01629/

## Key facts

- Cited by 119 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Jul 2017.

## Built on by (most cited first, 30 of 119)

- [Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions](https://mlsanity.com/paper/2102.12122/) (2021)
- [VMamba: Visual State Space Model](https://mlsanity.com/paper/2401.10166/) (2024)
- [CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windows](https://mlsanity.com/paper/2107.00652/) (2021)
- [Towards Real-World Blind Face Restoration with Generative Facial Prior](https://mlsanity.com/paper/2101.04061/) (2021)
- [Accuracy on the Line: On the Strong Correlation Between Out-of-Distribution and In-Distribution Generalization](https://mlsanity.com/paper/2107.04649/) (2021)
- [VOLO: Vision Outlooker for Visual Recognition](https://mlsanity.com/paper/2106.13112/) (2021)
- [Rethinking Rotated Object Detection with Gaussian Wasserstein Distance Loss](https://mlsanity.com/paper/2101.11952/) (2021)
- [Recent advances and clinical applications of deep learning in medical image analysis](https://mlsanity.com/paper/2105.13381/) (2021)
- [Agreement-on-the-Line: Predicting the Performance of Neural Networks under Distribution Shift](https://mlsanity.com/paper/2206.13089/) (2022)
- [The KFIoU Loss for Rotated Object Detection](https://mlsanity.com/paper/2201.12558/) (2022)
- [ELF-VC: Efficient Learned Flexible-Rate Video Coding](https://mlsanity.com/paper/2104.14335/) (2021)
- [Compute and Energy Consumption Trends in Deep Learning Inference](https://mlsanity.com/paper/2109.05472/) (2021)
- [Harmonizing the object recognition strategies of deep neural networks with humans](https://mlsanity.com/paper/2211.04533/) (2022)
- [No One Representation to Rule Them All: Overlapping Features of Training Methods](https://mlsanity.com/paper/2110.12899/) (2021)
- [Data Poisoning Won't Save You From Facial Recognition](https://mlsanity.com/paper/2106.14851/) (2021)
- [RegNet: Self-Regulated Network for Image Classification](https://mlsanity.com/paper/2101.00590/) (2021)
- [Domain Generalization using Pretrained Models without Fine-tuning](https://mlsanity.com/paper/2203.04600/) (2022)
- [Refining activation downsampling with SoftPool](https://mlsanity.com/paper/2101.00440/) (2021)
- [Face.evoLVe: A High-Performance Face Recognition Library](https://mlsanity.com/paper/2107.08621/) (2021)
- [Rethinking Bias Mitigation: Fairer Architectures Make for Fairer Face Recognition](https://mlsanity.com/paper/2210.09943/) (2022)
- [Fusing Higher-order Features in Graph Neural Networks for Skeleton-based Action Recognition](https://mlsanity.com/paper/2105.01563/) (2021)
- [Augmenting Deep Classifiers with Polynomial Neural Networks](https://mlsanity.com/paper/2104.07916/) (2021)
- [Controllable Guide-Space for Generalizable Face Forgery Detection](https://mlsanity.com/paper/2307.14039/) (2023)
- [CNN Filter DB: An Empirical Investigation of Trained Convolutional Filters](https://mlsanity.com/paper/2203.15331/) (2022)
- [Performance-optimized deep neural networks are evolving into worse models of inferotemporal visual cortex](https://mlsanity.com/paper/2306.03779/) (2023)
- [The 3D-PC: a benchmark for visual perspective taking in humans and machines](https://mlsanity.com/paper/2406.04138/) (2024)
- [Performance Evaluation of Deep Transfer Learning on Multiclass Identification of Common Weed Species in Cotton Production Systems](https://mlsanity.com/paper/2110.04960/) (2021)
- [Activated Gradients for Deep Neural Networks](https://mlsanity.com/paper/2107.04228/) (2021)
- [SparX: A Sparse Cross-Layer Connection Mechanism for Hierarchical Vision Mamba and Transformer Networks](https://mlsanity.com/paper/2409.09649/) (2024)
- [Recurrence along Depth: Deep Convolutional Neural Networks with Recurrent Layer Aggregation](https://mlsanity.com/paper/2110.11852/) (2021)

## Abstract (arXiv)

In this work, we present a simple, highly efficient and modularized Dual Path Network (DPN) for image classification which presents a new topology of connection paths internally. By revealing the equivalence of the state-of-the-art Residual Network (ResNet) and Densely Convolutional Network (DenseNet) within the HORNN framework, we find that ResNet enables feature re-usage while DenseNet enables new features exploration which are both important for learning good representations. To enjoy the benefits from both path topologies, our proposed Dual Path Network shares common features while maintaining the flexibility to explore new features through dual path architectures. Extensive experiments on three benchmark datasets, ImagNet-1k, Places365 and PASCAL VOC, clearly demonstrate superior performance of the proposed DPN over state-of-the-arts. In particular, on the ImagNet-1k dataset, a shallow DPN surpasses the best ResNeXt-101(64x4d) with 26% smaller model size, 25% less computational cost and 8% lower memory consumption, and a deeper DPN (DPN-131) further pushes the state-of-the-art single model performance with about 2 times faster training speed. Experiments on the Places365 large-scale scene dataset, PASCAL VOC detection dataset, and PASCAL VOC segmentation dataset also demonstrate its consistently better performance than DenseNet, ResNet and the latest ResNeXt model over various applications.