Learning Words by Drawing Images

By D'idac Sur'is, Adrià Recasens, David Bau, David F. Harwath, James R. Glass, Antonio Torralba. 2019

9 citations recorded by the source corpus.

We propose a framework for learning through drawing. Our goal is to learn the correspondence between spoken words and abstract visual attributes, from a dataset of spoken descriptions of images. Building upon recent findings that GAN representations can be manipulated to edit semantic concepts in the generated output, we propose a new method to use such GAN-generated images to train a model using a triplet loss. To apply the method, we develop Audio CLEVRGAN, a new dataset of audio descriptions of GAN-generated CLEVR images, and we describe a training procedure that creates a curriculum of GAN-generated images that focuses training on image pairs that differ in a specific, informative way. Training is done without additional supervision beyond the spoken captions and the GAN. We find that training that takes advantage of GAN-generated edited examples results in improvements in the model's ability to learn attributes compared to previous results. Our proposed learning framework also results in models that can associate spoken words with some abstract visual concepts such as color and size.

Subfields: Computer Vision and Pattern Recognition, Multimodal Learning, Representation & Self-Supervised Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Multimodal Learning

In Representation & Self-Supervised Learning

Citations in the corpus

Learning Hierarchical Discrete Linguistic Units from Visually-Grounded Speech (2019, background): “Subsequent work on visually-grounded models of speech has investigated improvements and alternatives to the modeling or training algorithms (Leidal et al., 2017; Kamper et al., 2017c; Havard et al., 2019a; Merkx et al., 2019; Chrupała et al., 2017; Scharenborg et al., 2018; Kamper et al., 2019b;a; S”
Text-Free Image-to-Speech Synthesis Using Learned Segmental Units (2020, background): “A rich body of work has recently emerged investigating representation learning for speech using visual grounding objectives (Synnaeve et al., 2014; Harwath and Glass, 2015; Harwath et al., 2016; Kamper et al., 2017; Havard et al., 2019a; Merkx et al., 2019; Chrupała et al., 2017; Alishahi et al., 20”
Adversarial Text-to-Image Synthesis: A Review (2021, background): “Speech and Video Building upon the progress made in T2I, multiple recent works proposed and investigated methods for speech-to-image synthesis (S2I) [180, 181, 182, 183].”