# HitNet: a neural network with capsules embedded in a Hit-or-Miss layer, extended with hybrid data augmentation and ghost capsules

arXiv: https://arxiv.org/abs/1806.06519 · HTML: https://mlsanity.com/paper/1806.06519/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 18 Jun 2018.

## Built on by (most cited first, 7 of 7)

- [WideCaps: A Wide Attention based Capsule Network for Image Classification](https://mlsanity.com/paper/2108.03627/) (2021)
- [Ghost Loss to Question the Reliability of Training Data](https://mlsanity.com/paper/2109.01504/) (2021)
- [Capsule networks with non-iterative cluster routing](https://mlsanity.com/paper/2109.09213/) (2021)
- [ME-CapsNet: A Multi-Enhanced Capsule Networks with Routing Mechanism](https://mlsanity.com/paper/2203.15547/) (2022)
- [PDR-CapsNet: an Energy-Efficient Parallel Approach to Dynamic Routing in Capsule Networks](https://mlsanity.com/paper/2310.03212/) (2023)
- [Convolutional Fully-Connected Capsule Network (CFC-CapsNet): A Novel and Fast Capsule Network](https://mlsanity.com/paper/2511.05617/) (2025)
- [DL-CapsNet: A Deep and Light Capsule Network](https://mlsanity.com/paper/2512.00061/) (2025)

## Abstract (arXiv)

Neural networks designed for the task of classification have become a commodity in recent years. Many works target the development of better networks, which results in a complexification of their architectures with more layers, multiple sub-networks, or even the combination of multiple classifiers. In this paper, we show how to redesign a simple network to reach excellent performances, which are better than the results reproduced with CapsNet on several datasets, by replacing a layer with a Hit-or-Miss layer. This layer contains activated vectors, called capsules, that we train to hit or miss a central capsule by tailoring a specific centripetal loss function. We also show how our network, named HitNet, is capable of synthesizing a representative sample of the images of a given class by including a reconstruction network. This possibility allows to develop a data augmentation step combining information from the data space and the feature space, resulting in a hybrid data augmentation process. In addition, we introduce the possibility for HitNet, to adopt an alternative to the true target when needed by using the new concept of ghost capsules, which is used here to detect potentially mislabeled images in the training data.