Deep Relative Attributes

12/13/2015
by   Yaser Souri, et al.
0

Visual attributes are great means of describing images or scenes, in a way both humans and computers understand. In order to establish a correspondence between images and to be able to compare the strength of each property between images, relative attributes were introduced. However, since their introduction, hand-crafted and engineered features were used to learn increasingly complex models for the problem of relative attributes. This limits the applicability of those methods for more realistic cases. We introduce a deep neural network architecture for the task of relative attribute prediction. A convolutional neural network (ConvNet) is adopted to learn the features by including an additional layer (ranking layer) that learns to rank the images based on these features. We adopt an appropriate ranking loss to train the whole network in an end-to-end fashion. Our proposed method outperforms the baseline and state-of-the-art methods in relative attribute prediction on various coarse and fine-grained datasets. Our qualitative results along with the visualization of the saliency maps show that the network is able to learn effective features for each specific attribute. Source code of the proposed method is available at https://github.com/yassersouri/ghiaseddin.

READ FULL TEXT

page 12

page 14

research
09/09/2020

Relative Attribute Classification with Deep Rank SVM

Relative attributes indicate the strength of a particular attribute betw...
research
08/09/2016

End-to-End Localization and Ranking for Relative Attributes

We propose an end-to-end deep convolutional network to simultaneously lo...
research
04/10/2022

Fashionformer: A simple, Effective and Unified Baseline for Human Fashion Segmentation and Recognition

Human fashion understanding is one important computer vision task since ...
research
04/01/2020

Symmetry and Group in Attribute-Object Compositions

Attributes and objects can compose diverse compositions. To model the co...
research
10/09/2021

Learning Single/Multi-Attribute of Object with Symmetry and Group

Attributes and objects can compose diverse compositions. To model the co...
research
12/19/2016

Semantic Jitter: Dense Supervision for Visual Comparisons via Synthetic Images

Distinguishing subtle differences in attributes is valuable, yet learnin...
research
05/25/2016

Describing Human Aesthetic Perception by Deeply-learned Attributes from Flickr

Many aesthetic models in computer vision suffer from two shortcomings: 1...

Please sign up or login with your details

Forgot password? Click here to reset