Artistic Object Recognition by Unsupervised Style Adaptation

12/28/2018
by   Christopher Thomas, et al.
0

Computer vision systems currently lack the ability to reliably recognize artistically rendered objects, especially when such data is limited. In this paper, we propose a method for recognizing objects in artistic modalities (such as paintings, cartoons, or sketches), without requiring any labeled data from those modalities. Our method explicitly accounts for stylistic domain shifts between and within domains. To do so, we introduce a complementary training modality constructed to be similar in artistic style to the target domain, and enforce that the network learns features that are invariant between the two training modalities. We show how such artificial labeled source domains can be generated automatically through the use of style transfer techniques, using diverse target images to represent the style in the target domain. Unlike existing methods which require a large amount of unlabeled target data, our method can work with as few as ten unlabeled images. We evaluate it on a number of cross-domain object and scene classification tasks and on a new dataset we release. Our experiments show that our approach, though conceptually simple, significantly improves the accuracy that existing domain adaptation techniques obtain for artistic object recognition.

READ FULL TEXT
research
07/31/2019

Unsupervised Domain Adaptation via Disentangled Representations: Application to Cross-Modality Liver Segmentation

A deep learning model trained on some labeled data from a certain source...
research
04/15/2022

Learning to Adapt Domain Shifts of Moral Values via Instance Weighting

Classifying moral values in user-generated text from social media is cri...
research
02/13/2019

Learning to see across Domains and Modalities

Deep learning has raised hopes and expectations as a general solution fo...
research
07/12/2016

Deep Reconstruction-Classification Networks for Unsupervised Domain Adaptation

In this paper, we propose a novel unsupervised domain adaptation algorit...
research
02/13/2023

In Search for a Generalizable Method for Source Free Domain Adaptation

Source-free domain adaptation (SFDA) is compelling because it allows ada...
research
11/06/2022

Motion Style Transfer: Modular Low-Rank Adaptation for Deep Motion Forecasting

Deep motion forecasting models have achieved great success when trained ...

Please sign up or login with your details

Forgot password? Click here to reset