# ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blocks

arXiv: https://arxiv.org/abs/1908.03930 · HTML: https://mlsanity.com/paper/1908.03930/

## Key facts

- Cited by 178 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Aug 2019.

## Built on by (most cited first, 30 of 178)

- [YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors](https://mlsanity.com/paper/2207.02696/) (2022)
- [RepVGG: Making VGG-style ConvNets Great Again](https://mlsanity.com/paper/2101.03697/) (2021)
- [HRDA: Context-Aware High-Resolution Domain-Adaptive Semantic Segmentation](https://mlsanity.com/paper/2204.13132/) (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)
- [More ConvNets in the 2020s: Scaling up Kernels Beyond 51x51 using Sparsity](https://mlsanity.com/paper/2207.03620/) (2022)
- [Salient Object Detection via Integrity Learning](https://mlsanity.com/paper/2101.07663/) (2021)
- [RepViT: Revisiting Mobile CNN From ViT Perspective](https://mlsanity.com/paper/2307.09283/) (2023)
- [Self-Sustaining Representation Expansion for Non-Exemplar Class-Incremental Learning](https://mlsanity.com/paper/2203.06359/) (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)
- [Diverse Branch Block: Building a Convolution as an Inception-like Unit](https://mlsanity.com/paper/2103.13425/) (2021)
- [What Makes Convolutional Models Great on Long Sequence Modeling?](https://mlsanity.com/paper/2210.09298/) (2022)
- [Towards Efficient Visual Adaption via Structural Re-parameterization](https://mlsanity.com/paper/2302.08106/) (2023)
- [Representation Compensation Networks for Continual Semantic Segmentation](https://mlsanity.com/paper/2203.05402/) (2022)
- [MotionTrack: Learning Robust Short-term and Long-term Motions for Multi-Object Tracking](https://mlsanity.com/paper/2303.10404/) (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)
- [Initialization and Regularization of Factorized Neural Layers](https://mlsanity.com/paper/2105.01029/) (2021)
- [Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR-based Perception](https://mlsanity.com/paper/2109.05441/) (2021)
- [FiLo: Zero-Shot Anomaly Detection by Fine-Grained Description and High-Quality Localization](https://mlsanity.com/paper/2404.13671/) (2024)
- [ClipSAM: CLIP and SAM Collaboration for Zero-Shot Anomaly Segmentation](https://mlsanity.com/paper/2401.12665/) (2024)
- [QKFormer: Hierarchical Spiking Transformer using Q-K Attention](https://mlsanity.com/paper/2403.16552/) (2024)
- [NORM: Knowledge Distillation via N-to-One Representation Matching](https://mlsanity.com/paper/2305.13803/) (2023)
- [CTNet: Context-based Tandem Network for Semantic Segmentation](https://mlsanity.com/paper/2104.09805/) (2021)
- [RepMLP: Re-parameterizing Convolutions into Fully-connected Layers for Image Recognition](https://mlsanity.com/paper/2105.01883/) (2021)
- [NTIRE 2022 Challenge on Efficient Super-Resolution: Methods and Results](https://mlsanity.com/paper/2205.05675/) (2022)
- [NTIRE 2024 Challenge on Image Super-Resolution (x4): Methods and Results](https://mlsanity.com/paper/2404.09790/) (2024)
- [Overview of Deep Learning-based CSI Feedback in Massive MIMO Systems](https://mlsanity.com/paper/2206.14383/) (2022)
- [Efficient Real-world Image Super-Resolution Via Adaptive Directional Gradient Convolution](https://mlsanity.com/paper/2405.07023/) (2024)
- [Improved Implicit Neural Representation with Fourier Reparameterized Training](https://mlsanity.com/paper/2401.07402/) (2024)

## Abstract (arXiv)

As designing appropriate Convolutional Neural Network (CNN) architecture in the context of a given application usually involves heavy human works or numerous GPU hours, the research community is soliciting the architecture-neutral CNN structures, which can be easily plugged into multiple mature architectures to improve the performance on our real-world applications. We propose Asymmetric Convolution Block (ACB), an architecture-neutral structure as a CNN building block, which uses 1D asymmetric convolutions to strengthen the square convolution kernels. For an off-the-shelf architecture, we replace the standard square-kernel convolutional layers with ACBs to construct an Asymmetric Convolutional Network (ACNet), which can be trained to reach a higher level of accuracy. After training, we equivalently convert the ACNet into the same original architecture, thus requiring no extra computations anymore. We have observed that ACNet can improve the performance of various models on CIFAR and ImageNet by a clear margin. Through further experiments, we attribute the effectiveness of ACB to its capability of enhancing the model's robustness to rotational distortions and strengthening the central skeleton parts of square convolution kernels.