# Res2Net: A New Multi-scale Backbone Architecture

arXiv: https://arxiv.org/abs/1904.01169 · HTML: https://mlsanity.com/paper/1904.01169/

## Key facts

- Cited by 470 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Apr 2019.

## Built on by (most cited first, 30 of 470)

- [Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions](https://mlsanity.com/paper/2102.12122/) (2021)
- [Multiscale Vision Transformers](https://mlsanity.com/paper/2104.11227/) (2021)
- [BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-View](https://mlsanity.com/paper/2112.11790/) (2021)
- [YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information](https://mlsanity.com/paper/2402.13616/) (2024)
- [SegNeXt: Rethinking Convolutional Attention Design for Semantic Segmentation](https://mlsanity.com/paper/2209.08575/) (2022)
- [Concealed Object Detection](https://mlsanity.com/paper/2102.10274/) (2021)
- [Visual Attention Network](https://mlsanity.com/paper/2202.09741/) (2022)
- [Probabilistic two-stage detection](https://mlsanity.com/paper/2103.07461/) (2021)
- [MPViT: Multi-Path Vision Transformer for Dense Prediction](https://mlsanity.com/paper/2112.11010/) (2021)
- [Towards Large-Scale Small Object Detection: Survey and Benchmarks](https://mlsanity.com/paper/2207.14096/) (2022)
- [EdgeNeXt: Efficiently Amalgamated CNN-Transformer Architecture for Mobile Vision Applications](https://mlsanity.com/paper/2206.10589/) (2022)
- [Highly Accurate Dichotomous Image Segmentation](https://mlsanity.com/paper/2203.03041/) (2022)
- [Global Tracking Transformers](https://mlsanity.com/paper/2203.13250/) (2022)
- [Shallow Attention Network for Polyp Segmentation](https://mlsanity.com/paper/2108.00882/) (2021)
- [Masked Generative Distillation](https://mlsanity.com/paper/2205.01529/) (2022)
- [Large-scale Unsupervised Semantic Segmentation](https://mlsanity.com/paper/2106.03149/) (2021)
- [UniTS: A Unified Multi-Task Time Series Model](https://mlsanity.com/paper/2403.00131/) (2024)
- [CAT: Cross Attention in Vision Transformer](https://mlsanity.com/paper/2106.05786/) (2021)
- [Contextual Transformer Networks for Visual Recognition](https://mlsanity.com/paper/2107.12292/) (2021)
- [Deep Dual-resolution Networks for Real-time and Accurate Semantic Segmentation of Road Scenes](https://mlsanity.com/paper/2101.06085/) (2021)
- [Context-aware Cross-level Fusion Network for Camouflaged Object Detection](https://mlsanity.com/paper/2105.12555/) (2021)
- [Weakly Supervised Object Localization and Detection: A Survey](https://mlsanity.com/paper/2104.07918/) (2021)
- [P2T: Pyramid Pooling Transformer for Scene Understanding](https://mlsanity.com/paper/2106.12011/) (2021)
- [Video Polyp Segmentation: A Deep Learning Perspective](https://mlsanity.com/paper/2203.14291/) (2022)
- [Conv2Former: A Simple Transformer-Style ConvNet for Visual Recognition](https://mlsanity.com/paper/2211.11943/) (2022)
- [High-resolution Iterative Feedback Network for Camouflaged Object Detection](https://mlsanity.com/paper/2203.11624/) (2022)
- [Wave-ViT: Unifying Wavelet and Transformers for Visual Representation Learning](https://mlsanity.com/paper/2207.04978/) (2022)
- [CBNet: A Composite Backbone Network Architecture for Object Detection](https://mlsanity.com/paper/2107.00420/) (2021)
- [Vision-Language-Action (VLA) Models: Concepts, Progress, Applications and Challenges](https://mlsanity.com/paper/2505.04769/) (2025)
- [Multi-Scale Spatial Temporal Graph Convolutional Network for Skeleton-Based Action Recognition](https://mlsanity.com/paper/2206.13028/) (2022)

## Abstract (arXiv)

Representing features at multiple scales is of great importance for numerous vision tasks. Recent advances in backbone convolutional neural networks (CNNs) continually demonstrate stronger multi-scale representation ability, leading to consistent performance gains on a wide range of applications. However, most existing methods represent the multi-scale features in a layer-wise manner. In this paper, we propose a novel building block for CNNs, namely Res2Net, by constructing hierarchical residual-like connections within one single residual block. The Res2Net represents multi-scale features at a granular level and increases the range of receptive fields for each network layer. The proposed Res2Net block can be plugged into the state-of-the-art backbone CNN models, e.g., ResNet, ResNeXt, and DLA. We evaluate the Res2Net block on all these models and demonstrate consistent performance gains over baseline models on widely-used datasets, e.g., CIFAR-100 and ImageNet. Further ablation studies and experimental results on representative computer vision tasks, i.e., object detection, class activation mapping, and salient object detection, further verify the superiority of the Res2Net over the state-of-the-art baseline methods. The source code and trained models are available on https://mmcheng.net/res2net/.