# HetConv: Heterogeneous Kernel-Based Convolutions for Deep CNNs

arXiv: https://arxiv.org/abs/1903.04120 · HTML: https://mlsanity.com/paper/1903.04120/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Mar 2019.

## Built on by (most cited first, 16 of 16)

- [Run, Don't Walk: Chasing Higher FLOPS for Faster Neural Networks](https://mlsanity.com/paper/2303.03667/) (2023)
- [Multimodal Fusion Transformer for Remote Sensing Image Classification](https://mlsanity.com/paper/2203.16952/) (2022)
- [Efficient Feature Transformations for Discriminative and Generative Continual Learning](https://mlsanity.com/paper/2103.13558/) (2021)
- [Learning Visual Affordance Grounding from Demonstration Videos](https://mlsanity.com/paper/2108.05675/) (2021)
- [Block Walsh-Hadamard Transform Based Binary Layers in Deep Neural Networks](https://mlsanity.com/paper/2201.02711/) (2022)
- [Learned Video Compression via Heterogeneous Deformable Compensation Network](https://mlsanity.com/paper/2207.04589/) (2022)
- [Infrared Image Super-Resolution via Heterogeneous Convolutional WGAN](https://mlsanity.com/paper/2109.00960/) (2021)
- [DualConv: Dual Convolutional Kernels for Lightweight Deep Neural Networks](https://mlsanity.com/paper/2202.07481/) (2022)
- [3D-Convolution Guided Spectral-Spatial Transformer for Hyperspectral Image Classification](https://mlsanity.com/paper/2404.13252/) (2024)
- [Pushing the Efficiency Limit Using Structured Sparse Convolutions](https://mlsanity.com/paper/2210.12818/) (2022)
- [Learnable Heterogeneous Convolution: Learning both topology and strength](https://mlsanity.com/paper/2301.05440/) (2023)
- [Shortcut-V2V: Compression Framework for Video-to-Video Translation based on Temporal Redundancy Reduction](https://mlsanity.com/paper/2308.08011/) (2023)
- [A Fast and Efficient Conditional Learning for Tunable Trade-Off between Accuracy and Robustness](https://mlsanity.com/paper/2204.00426/) (2022)
- [Real-Time AIoT for AAV Antenna Interference Detection via Edge-Cloud Collaboration](https://mlsanity.com/paper/2412.03055/) (2024)
- [MMFormer: Multimodal Transformer Using Multiscale Self-Attention for Remote Sensing Image Classification](https://mlsanity.com/paper/2303.13101/) (2023)
- [DeepTraverse: A Depth-First Search Inspired Network for Algorithmic Visual Understanding](https://mlsanity.com/paper/2506.10084/) (2025)

## Abstract (arXiv)

We present a novel deep learning architecture in which the convolution operation leverages heterogeneous kernels. The proposed HetConv (Heterogeneous Kernel-Based Convolution) reduces the computation (FLOPs) and the number of parameters as compared to standard convolution operation while still maintaining representational efficiency. To show the effectiveness of our proposed convolution, we present extensive experimental results on the standard convolutional neural network (CNN) architectures such as VGG citevgg2014very and ResNet citeresnet. We find that after replacing the standard convolutional filters in these architectures with our proposed HetConv filters, we achieve 3X to 8X FLOPs based improvement in speed while still maintaining (and sometimes improving) the accuracy. We also compare our proposed convolutions with group/depth wise convolutions and show that it achieves more FLOPs reduction with significantly higher accuracy.