Semantic Jitter: Dense Supervision for Visual Comparisons via Synthetic Images
Authors:
- Aron YuAYAron Yu
- Kristen GraumanKGKristen Grauman
- 1 October 2017
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 5571-5580
Abstract
Distinguishing subtle differences in attributes is valuable, yet learning to make visual comparisons remains nontrivial. Not only is the number of possible comparisons quadratic in the number of training images, but also access to images adequately spanning the space of fine-grained visual differences is limited. We propose to overcome the sparsity of supervision problem via synthetically generated images. Building on a state-of-the-art image generation engine, we sample pairs of training images exhibiting slight modifications of individual attributes. Augmenting real training image pairs with these examples, we then train attribute ranking models to predict the relative strength of an attribute in novel pairs of real images. Our results on datasets of faces and fashion images show the great promise of bootstrapping imperfect image generators to counteract sample sparsity for learning to rank.Keywords
All Related Versions
This publication has 35 references indexed in Scilit:
- End-to-End Localization and Ranking for Relative Attributes2016
- Learning Deep Object Detectors from 3D Models2015
- Relative Parts: Distinctive Parts for Learning Relative Attributes2014
- Human identification using facial comparative descriptions2013
- Constrained Semi-Supervised Learning Using Attributes and Comparative Attributes2012
- Relative attributes2011
- Real-time human pose recognition in parts from single depth images2011
- In Good Shape: Robust People Detection based on Appearance and Shape2011
- Best practices for convolutional neural networks applied to visual document analysis2005
- Fast pose estimation with parameter-sensitive hashing2003