# Convolution in Convolution for Network in Network

arXiv: https://arxiv.org/abs/1603.06759 · HTML: https://mlsanity.com/paper/1603.06759/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Mar 2016.

## Built on by (most cited first, 9 of 9)

- [A Survey of Visual Transformers](https://mlsanity.com/paper/2111.06091/) (2021)
- [Mamba-UIE: Enhancing Underwater Images with Physical Model Constraint](https://mlsanity.com/paper/2407.19248/) (2024)
- [Semi-Supervised Weed Detection for Rapid Deployment and Enhanced Efficiency](https://mlsanity.com/paper/2405.07399/) (2024)
- [Improving Robustness of Deep Convolutional Neural Networks via Multiresolution Learning](https://mlsanity.com/paper/2309.13752/) (2023)
- [Generalized Activation via Multivariate Projection](https://mlsanity.com/paper/2309.17194/) (2023)
- [3DPyranet Features Fusion for Spatio-temporal Feature Learning](https://mlsanity.com/paper/2504.18977/) (2025)
- [BioAutoML-NAS: An End-to-End AutoML Framework for Multimodal Insect Classification via Neural Architecture Search on Large-Scale Biodiversity Data](https://mlsanity.com/paper/2510.05888/) (2025)
- [MATS: A novel multi-modality multi-task learning framework for 3D perception in autonomous driving](https://mlsanity.com/paper/2607.24224/) (2026)
- [A Comprehensive Review of One-Pixel Attack: Research Status, Taxonomy, Applications, Regulation Policy and Future Directions](https://mlsanity.com/paper/2610.00125/) (2026)

## Abstract (arXiv)

Network in Netwrok (NiN) is an effective instance and an important extension of Convolutional Neural Network (CNN) consisting of alternating convolutional layers and pooling layers. Instead of using a linear filter for convolution, NiN utilizes shallow MultiLayer Perceptron (MLP), a nonlinear function, to replace the linear filter. Because of the powerfulness of MLP and  1× 1  convolutions in spatial domain, NiN has stronger ability of feature representation and hence results in better recognition rate. However, MLP itself consists of fully connected layers which give rise to a large number of parameters. In this paper, we propose to replace dense shallow MLP with sparse shallow MLP. One or more layers of the sparse shallow MLP are sparely connected in the channel dimension or channel-spatial domain. The proposed method is implemented by applying unshared convolution across the channel dimension and applying shared convolution across the spatial dimension in some computational layers. The proposed method is called CiC. Experimental results on the CIFAR10 dataset, augmented CIFAR10 dataset, and CIFAR100 dataset demonstrate the effectiveness of the proposed CiC method.