# DiCENet: Dimension-wise Convolutions for Efficient Networks

arXiv: https://arxiv.org/abs/1906.03516 · HTML: https://mlsanity.com/paper/1906.03516/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Jun 2019.

## Built on by (most cited first, 6 of 6)

- [MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer](https://mlsanity.com/paper/2110.02178/) (2021)
- [Topology-Aware Network Pruning using Multi-stage Graph Embedding and Reinforcement Learning](https://mlsanity.com/paper/2102.03214/) (2021)
- [Exposing Semantic Segmentation Failures via Maximum Discrepancy Competition](https://mlsanity.com/paper/2103.00259/) (2021)
- [A Survey on Deep Domain Adaptation and Tiny Object Detection Challenges, Techniques and Datasets](https://mlsanity.com/paper/2107.07927/) (2021)
- [ImageSig: A signature transform for ultra-lightweight image recognition](https://mlsanity.com/paper/2205.06929/) (2022)
- [To Perceive or Not to Perceive: Lightweight Stacked Hourglass Network](https://mlsanity.com/paper/2302.04815/) (2023)

## Abstract (arXiv)

We introduce a novel and generic convolutional unit, DiCE unit, that is built using dimension-wise convolutions and dimension-wise fusion. The dimension-wise convolutions apply light-weight convolutional filtering across each dimension of the input tensor while dimension-wise fusion efficiently combines these dimension-wise representations; allowing the DiCE unit to efficiently encode spatial and channel-wise information contained in the input tensor. The DiCE unit is simple and can be seamlessly integrated with any architecture to improve its efficiency and performance. Compared to depth-wise separable convolutions, the DiCE unit shows significant improvements across different architectures. When DiCE units are stacked to build the DiCENet model, we observe significant improvements over state-of-the-art models across various computer vision tasks including image classification, object detection, and semantic segmentation. On the ImageNet dataset, the DiCENet delivers 2-4% higher accuracy than state-of-the-art manually designed models (e.g., MobileNetv2 and ShuffleNetv2). Also, DiCENet generalizes better to tasks (e.g., object detection) that are often used in resource-constrained devices in comparison to state-of-the-art separable convolution-based efficient networks, including neural search-based methods (e.g., MobileNetv3 and MixNet. Our source code in PyTorch is open-source and is available at https://github.com/sacmehta/EdgeNets/