# Diverse Branch Block: Building a Convolution as an Inception-like Unit

arXiv: https://arxiv.org/abs/2103.13425 · HTML: https://mlsanity.com/paper/2103.13425/

## Key facts

- Cited by 87 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 39 references that are in the map.
- First posted on arXiv 24 Mar 2021.

## Builds on (most cited first, 30 of 32)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [Pyramid Scene Parsing Network](https://mlsanity.com/paper/1612.01105/) (2016)
- [DARTS: Differentiable Architecture Search](https://mlsanity.com/paper/1806.09055/) (2018)
- [Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning](https://mlsanity.com/paper/1602.07261/) (2016)
- [Neural Architecture Search with Reinforcement Learning](https://mlsanity.com/paper/1611.01578/) (2016)
- [Deformable Convolutional Networks](https://mlsanity.com/paper/1703.06211/) (2017)
- [ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices](https://mlsanity.com/paper/1707.01083/) (2017)
- [Objects as Points](https://mlsanity.com/paper/1904.07850/) (2019)
- [ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design](https://mlsanity.com/paper/1807.11164/) (2018)
- [Multi-Scale Context Aggregation by Dilated Convolutions](https://mlsanity.com/paper/1511.07122/) (2015)
- [Regularized Evolution for Image Classifier Architecture Search](https://mlsanity.com/paper/1802.01548/) (2018)
- [ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks](https://mlsanity.com/paper/1910.03151/) (2019)
- [RepVGG: Making VGG-style ConvNets Great Again](https://mlsanity.com/paper/2101.03697/) (2021)
- [Progressive Neural Architecture Search](https://mlsanity.com/paper/1712.00559/) (2017)
- [Making Convolutional Networks Shift-Invariant Again](https://mlsanity.com/paper/1904.11486/) (2019)
- [CondConv: Conditionally Parameterized Convolutions for Efficient Inference](https://mlsanity.com/paper/1904.04971/) (2019)
- [ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blocks](https://mlsanity.com/paper/1908.03930/) (2019)
- [Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convolution](https://mlsanity.com/paper/1904.05049/) (2019)
- [ExpandNets: Linear Over-parameterization to Train Compact Convolutional Networks](https://mlsanity.com/paper/1811.10495/) (2018)

## Built on by (most cited first, 30 of 87)

- [YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors](https://mlsanity.com/paper/2207.02696/) (2022)
- [FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterization](https://mlsanity.com/paper/2303.14189/) (2023)
- [Scaling Up Your Kernels to 31x31: Revisiting Large Kernel Design in CNNs](https://mlsanity.com/paper/2203.06717/) (2022)
- [MobileOne: An Improved One millisecond Mobile Backbone](https://mlsanity.com/paper/2206.04040/) (2022)
- [MobileCLIP: Fast Image-Text Models through Multi-Modal Reinforced Training](https://mlsanity.com/paper/2311.17049/) (2023)
- [Towards Efficient Visual Adaption via Structural Re-parameterization](https://mlsanity.com/paper/2302.08106/) (2023)
- [UniRepLKNet: A Universal Perception Large-Kernel ConvNet for Audio, Video, Point Cloud, Time-Series and Image Recognition](https://mlsanity.com/paper/2311.15599/) (2023)
- [Multi-Task Dense Prediction via Mixture of Low-Rank Experts](https://mlsanity.com/paper/2403.17749/) (2024)
- [The Ninth NTIRE 2024 Efficient Super-Resolution Challenge Report](https://mlsanity.com/paper/2404.10343/) (2024)
- [Lightweight Adaptive Feature De-drifting for Compressed Image Classification](https://mlsanity.com/paper/2401.01724/) (2024)
- [NTIRE 2022 Challenge on Efficient Super-Resolution: Methods and Results](https://mlsanity.com/paper/2205.05675/) (2022)
- [Re-parameterizing Your Optimizers rather than Architectures](https://mlsanity.com/paper/2205.15242/) (2022)
- [RepMLPNet: Hierarchical Vision MLP with Re-parameterized Locality](https://mlsanity.com/paper/2112.11081/) (2021)
- [Towards Local Visual Modeling for Image Captioning](https://mlsanity.com/paper/2302.06098/) (2023)
- [The Tenth NTIRE 2025 Efficient Super-Resolution Challenge Report](https://mlsanity.com/paper/2504.10686/) (2025)
- [VanillaNet: the Power of Minimalism in Deep Learning](https://mlsanity.com/paper/2305.12972/) (2023)
- [Make RepVGG Greater Again: A Quantization-aware Approach](https://mlsanity.com/paper/2212.01593/) (2022)
- [RepSR: Training Efficient VGG-style Super-Resolution Networks with Structural Re-Parameterization and Batch Normalization](https://mlsanity.com/paper/2205.05671/) (2022)
- [Edge-enhanced Feature Distillation Network for Efficient Super-Resolution](https://mlsanity.com/paper/2204.08759/) (2022)
- [Consolidator: Mergeable Adapter with Grouped Connections for Visual Adaptation](https://mlsanity.com/paper/2305.00603/) (2023)
- [Efficient and Accurate Quantized Image Super-Resolution on Mobile NPUs, Mobile AI & AIM 2022 challenge: Report](https://mlsanity.com/paper/2211.05910/) (2022)
- [GhostNetV3: Exploring the Training Strategies for Compact Models](https://mlsanity.com/paper/2404.11202/) (2024)
- [DAMO-StreamNet: Optimizing Streaming Perception in Autonomous Driving](https://mlsanity.com/paper/2303.17144/) (2023)
- [APG: Adaptive Parameter Generation Network for Click-Through Rate Prediction](https://mlsanity.com/paper/2203.16218/) (2022)
- [Online Video Super-Resolution with Convolutional Kernel Bypass Graft](https://mlsanity.com/paper/2208.02470/) (2022)
- [Experts Weights Averaging: A New General Training Scheme for Vision Transformers](https://mlsanity.com/paper/2308.06093/) (2023)
- [MobileIE: An Extremely Lightweight and Effective ConvNet for Real-Time Image Enhancement on Mobile Devices](https://mlsanity.com/paper/2507.01838/) (2025)
- [RepNAS: Searching for Efficient Re-parameterizing Blocks](https://mlsanity.com/paper/2109.03508/) (2021)
- [DyRep: Bootstrapping Training with Dynamic Re-parameterization](https://mlsanity.com/paper/2203.12868/) (2022)
- [Residual Spatial Fusion Network for RGB-Thermal Semantic Segmentation](https://mlsanity.com/paper/2306.10364/) (2023)

## Abstract (arXiv)

We propose a universal building block of Convolutional Neural Network (ConvNet) to improve the performance without any inference-time costs. The block is named Diverse Branch Block (DBB), which enhances the representational capacity of a single convolution by combining diverse branches of different scales and complexities to enrich the feature space, including sequences of convolutions, multi-scale convolutions, and average pooling. After training, a DBB can be equivalently converted into a single conv layer for deployment. Unlike the advancements of novel ConvNet architectures, DBB complicates the training-time microstructure while maintaining the macro architecture, so that it can be used as a drop-in replacement for regular conv layers of any architecture. In this way, the model can be trained to reach a higher level of performance and then transformed into the original inference-time structure for inference. DBB improves ConvNets on image classification (up to 1.9% higher top-1 accuracy on ImageNet), object detection and semantic segmentation. The PyTorch code and models are released at https://github.com/DingXiaoH/DiverseBranchBlock.