Large-Scale Attribute-Object Compositions

05/24/2021
by   Filip Radenovic, et al.
0

We study the problem of learning how to predict attribute-object compositions from images, and its generalization to unseen compositions missing from the training data. To the best of our knowledge, this is a first large-scale study of this problem, involving hundreds of thousands of compositions. We train our framework with images from Instagram using hashtags as noisy weak supervision. We make careful design choices for data collection and modeling, in order to handle noisy annotations and unseen compositions. Finally, extensive evaluations show that learning to compose classifiers outperforms late fusion of individual attribute and object predictions, especially in the case of unseen attribute-object pairs.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 8

10/27/2020

Learning to Infer Unseen Attribute-Object Compositions

The composition recognition of unseen attribute-object is critical to ma...
12/08/2017

Class Rectification Hard Mining for Imbalanced Deep Learning

Recognising detailed facial or clothing attributes in images of people i...
10/15/2016

Recovering the Missing Link: Predicting Class-Attribute Associations for Unsupervised Zero-Shot Learning

Collecting training images for all visual categories is not only expensi...
05/15/2019

Task-Driven Modular Networks for Zero-Shot Compositional Learning

One of the hallmarks of human intelligence is the ability to compose lea...
11/18/2019

Attribute noise robust binary classification

We consider the problem of learning linear classifiers when both feature...
12/19/2016

Semantic Jitter: Dense Supervision for Visual Comparisons via Synthetic Images

Distinguishing subtle differences in attributes is valuable, yet learnin...
10/22/2020

Object-Attribute Biclustering for Elimination of Missing Genotypes in Ischemic Stroke Genome-Wide Data

Missing genotypes can affect the efficacy of machine learning approaches...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.