Learning What and Where to Draw

Scott E. Reed, Zeynep Akata, Santosh Mohan, Samuel Tenka, Bernt Schiele, and Honglak Lee. Learning what and where to draw. CoRR, abs/1610.02454, 2016. URL http://arxiv.org/abs/1610.02454.

Related Work / Contribution

A. Radford, L. Metz, and S. Chintala. Unsupervised representation learning with deep convolutional generative adversarial networks. In ICLR, 2016.

Dataset

Caltech-UCSD Birds (CUB) dataset ● ● ●

Over 11k images of 200 species 10 single sentence descriptions per image Bounding box and up to 15 bird part x, y coordinates

Dataset

MPII Human Pose (MPH) dataset ● ● ● ●

Used 19k of the 25k images (filtered out multiple people images) 410 common activities Keypoint coordinates for 16 joint types Crowdsourced to get 3 single-sentence descriptions for each image

Results