# Learning Gaussian Data Augmentation in Feature Space for One-shot Object Detection in Manga

arXiv: https://arxiv.org/abs/2410.05935 · HTML: https://mlsanity.com/paper/2410.05935/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 45 references that are in the map.
- First posted on arXiv 8 Oct 2024.

## Builds on (most cited first, 18 of 18)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Feature Pyramid Networks for Object Detection](https://mlsanity.com/paper/1612.03144/) (2016)
- [Improved Regularization of Convolutional Neural Networks with Cutout](https://mlsanity.com/paper/1708.04552/) (2017)
- [Random Erasing Data Augmentation](https://mlsanity.com/paper/1708.04896/) (2017)
- [Open-Vocabulary Object Detection Using Captions](https://mlsanity.com/paper/2011.10678/) (2020)
- [Synthetic Data Augmentation using GAN for Improved Liver Lesion Classification](https://mlsanity.com/paper/1801.02385/) (2018)
- [Return of the Devil in the Details: Delving Deep into Convolutional Nets](https://mlsanity.com/paper/1405.3531/) (2014)
- [Data Augmentation by Pairing Samples for Images Classification](https://mlsanity.com/paper/1801.02929/) (2018)
- [One-Shot Object Detection with Co-Attention and Co-Excitation](https://mlsanity.com/paper/1911.12529/) (2019)
- [Multi-level Semantic Feature Augmentation for One-shot Learning](https://mlsanity.com/paper/1804.05298/) (2018)
- [Data Augmentation Using GANs](https://mlsanity.com/paper/1904.09135/) (2019)
- [Learning Domain Adaptive Object Detection with Probabilistic Teacher](https://mlsanity.com/paper/2206.06293/) (2022)
- [One-Shot Instance Segmentation](https://mlsanity.com/paper/1811.11507/) (2018)
- [OS2D: One-Stage One-Shot Object Detection by Matching Anchor Features](https://mlsanity.com/paper/2003.06800/) (2020)
- [One-Shot Object Detection without Fine-Tuning](https://mlsanity.com/paper/2005.03819/) (2020)
- [Transform-Invariant Convolutional Neural Networks for Image Classification and Search](https://mlsanity.com/paper/1912.01447/) (2019)
- [Unconstrained Text Detection in Manga: a New Dataset and Baseline](https://mlsanity.com/paper/2009.04042/) (2020)
- [Feature transforms for image data augmentation](https://mlsanity.com/paper/2201.09700/) (2022)

## Built on by (most cited first, 2 of 2)

- [CAVE-Net: Classifying Abnormalities in Video Capsule Endoscopy](https://mlsanity.com/paper/2410.20231/) (2024)
- [Prompt-Driven Simulation with Feature Perturbation for Cross-Domain Few-Shot Object Detection](https://mlsanity.com/paper/2608.01348/) (2026)

## Abstract (arXiv)

We tackle one-shot object detection in Japanese Manga. The rising global popularity of Japanese manga has made the object detection of character faces increasingly important, with potential applications such as automatic colorization. However, obtaining sufficient data for training conventional object detectors is challenging due to copyright restrictions. Additionally, new characters appear every time a new volume of manga is released, making it impractical to re-train object detectors each time to detect these new characters. Therefore, one-shot object detection, where only a single query (reference) image is required to detect a new character, is an essential task in the manga industry. One challenge with one-shot object detection in manga is the large variation in the poses and facial expressions of characters in target images, despite having only one query image as a reference. Another challenge is that the frequency of character appearances follows a long-tail distribution. To overcome these challenges, we propose a data augmentation method in feature space to increase the variation of the query. The proposed method augments the feature from the query by adding Gaussian noise, with the noise variance at each channel learned during training. The experimental results show that the proposed method improves the performance for both seen and unseen classes, surpassing data augmentation methods in image space.