# ResNet or DenseNet? Introducing Dense Shortcuts to ResNet

arXiv: https://arxiv.org/abs/2010.12496 · HTML: https://mlsanity.com/paper/2010.12496/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Oct 2020.

## Built on by (most cited first, 12 of 12)

- [Learning Monocular Depth in Dynamic Scenes via Instance-Aware Projection Consistency](https://mlsanity.com/paper/2102.02629/) (2021)
- [Decoupled Adversarial Contrastive Learning for Self-supervised Adversarial Robustness](https://mlsanity.com/paper/2207.10899/) (2022)
- [Universal Adversarial Perturbations Through the Lens of Deep Steganography: Towards A Fourier Perspective](https://mlsanity.com/paper/2102.06479/) (2021)
- [Universal Adversarial Training with Class-Wise Perturbations](https://mlsanity.com/paper/2104.03000/) (2021)
- [Understanding Segment Anything Model: SAM is Biased Towards Texture Rather than Shape](https://mlsanity.com/paper/2311.11465/) (2023)
- [FedDebug: Systematic Debugging for Federated Learning Applications](https://mlsanity.com/paper/2301.03553/) (2023)
- [Fast Lossless Neural Compression with Integer-Only Discrete Flows](https://mlsanity.com/paper/2206.08869/) (2022)
- [Eye Know You Too: A DenseNet Architecture for End-to-end Eye Movement Biometrics](https://mlsanity.com/paper/2201.02110/) (2022)
- [Fortifying Fully Convolutional Generative Adversarial Networks for Image Super-Resolution Using Divergence Measures](https://mlsanity.com/paper/2404.06294/) (2024)
- [Towards Understanding Dual BN In Hybrid Adversarial Training](https://mlsanity.com/paper/2403.19150/) (2024)
- [RACH Traffic Prediction in Massive Machine Type Communications](https://mlsanity.com/paper/2405.05235/) (2024)
- [A Real-Time DDS-Based Chest X-Ray Decision Support System for Resource-Constrained Clinics](https://mlsanity.com/paper/2412.07818/) (2024)

## Abstract (arXiv)

ResNet or DenseNet? Nowadays, most deep learning based approaches are implemented with seminal backbone networks, among them the two arguably most famous ones are ResNet and DenseNet. Despite their competitive performance and overwhelming popularity, inherent drawbacks exist for both of them. For ResNet, the identity shortcut that stabilizes training also limits its representation capacity, while DenseNet has a higher capacity with multi-layer feature concatenation. However, the dense concatenation causes a new problem of requiring high GPU memory and more training time. Partially due to this, it is not a trivial choice between ResNet and DenseNet. This paper provides a unified perspective of dense summation to analyze them, which facilitates a better understanding of their core difference. We further propose dense weighted normalized shortcuts as a solution to the dilemma between them. Our proposed dense shortcut inherits the design philosophy of simple design in ResNet and DenseNet. On several benchmark datasets, the experimental results show that the proposed DSNet achieves significantly better results than ResNet, and achieves comparable performance as DenseNet but requiring fewer computation resources.