VISALOGY: Answering Visual Analogy Questions

Abstract

In this paper, we study the problem of answering visual analogy questions. These questions take the form of image A is to image B as image C is to what. Answering these questions entails discovering the mapping from image A to image B and then extending the mapping to image C and searching for the image D such that the relation from A to B holds for C to D. We pose this problem as learning an embedding that encourages pairs of analogous images with similar transformations to be close together using convolutional neural networks with a quadruple Siamese architecture. We introduce a dataset of visual analogy questions in natural images, and show first results of its kind on solving analogy questions on natural images.

To appear in NIPS 2015

References in corpus (2)

• From Frequency to Meaning: Vector Space Models of Semantics
• Unifying Visual-Semantic Embeddings with Multimodal Neural Language Models

Cited by in corpus (5)

• Abstraction and Analogy-Making in Artificial Intelligence
• Data-Driven Design-by-Analogy: State of the Art and Future Directions
• From A to Z: Supervised Transfer of Style and Content Using Deep Neural Network Generators
• Visual analogy: Deep learning versus compositional models
• Solving morphological analogies: from retrieval to generation