SITTA: Single Image Texture Translation for Data Augmentation

2021-06-25 · Boyi Li, Yin Cui, Tsung-Yi Lin, Serge Belongie

Recent advances in data augmentation enable one to translate images by learning the mapping between a source domain and a target domain. Existing methods tend to learn the distributions by training a model on a variety of datasets, with results evaluated largely in a subjective manner. Relatively few works in this area, however, study the potential use of image synthesis methods for recognition tasks. In this paper, we propose and explore the problem of image translation for data augmentation. We first propose a lightweight yet efficient model for translating texture to augment images based on a single input of source texture, allowing for fast training and testing, referred to as Single Image Texture Translation for data Augmentation (SITTA). Then we explore the use of augmented data in long-tailed and few-shot image classification tasks. We find the proposed augmentation method and workflow is capable of translating the texture of input data into a target domain, leading to consistently improved image recognition performance. Finally, we examine how SITTA and related image translation methods can provide a basis for a data-efficient, "augmentation engineering" approach to model training. Codes are available at https://github.com/Boyiliee/SITTA.

📄 PDF Abstract BibTeX arXiv:2106.13804

Code (2)

Boyiliee/SITT 공식 구현 pytorch

boyiliee/sitta 공식 구현 pytorch

Tasks

Data Augmentation Few-Shot Image Classification image-classification Image Classification Image Generation Translation

360-Degree Textures of People in Clothing from a Single Image

2019-08-20 · Verica Lazova, Eldar Insafutdinov, Gerard Pons-Moll

In this paper we predict a full 3D avatar of a person from a single image. We infer texture and geometry in the UV-space of the SMPL model using an image-to-image translation method. Given partial texture and segmentatio…

Image-to-Image Translation Translation

RIN: Textured Human Model Recovery and Imitation with a Single Image

2020-11-24 · Haoxi Ran, Guangfu Wang, Li Lu

Human imitation has become topical recently, driven by GAN's ability to disentangle human pose and body content. However, the latest methods hardly focus on 3D information, and to avoid self-occlusion, a massive amount o…

Translation

Depth Estimation from Single-shot Monocular Endoscope Image Using Image Domain Adaptation And Edge-Aware Depth Estimation

2022-01-12 · Masahiro Oda, Hayato Itoh, Kiyohito Tanaka, Hirotsugu TAKABATAKE 외

We propose a depth estimation method from a single-shot monocular endoscopic image using Lambertian surface translation by domain adaptation and depth estimation using multi-scale edge loss. We employ a two-step estimati…

Depth Estimation Domain Adaptation Translation

Rigid-Motion Scattering for Texture Classification

2014-03-07 · Laurent SIfre, Stéphane Mallat

A rigid-motion scattering computes adaptive invariants along translations and rotations, with a deep convolutional network. Convolutions are calculated on the rigid-motion group, with wavelets defined on the translation …

Classification General Classification Texture Classification Translation

Content Preserving Image Translation with Texture Co-occurrence and Spatial Self-Similarity for Texture Debiasing and Domain Adaptation

2021-10-15 · Myeongkyun Kang, Dongkyu Won, Miguel Luna, Philip Chikontwe 외

Models trained on datasets with texture bias usually perform poorly on out-of-distribution samples since biased representations are embedded into the model. Recently, various image translation and debiasing methods have …

Domain Adaptation Translation