Learning Predicates as Functions to Enable Few-shot Scene Graph Prediction

no code implementations • 12 Jun 2019 • Apoorva Dornadula, Austin Narcomey, Ranjay Krishna, Michael Bernstein, Li Fei-Fei

We introduce the first scene graph prediction model that supports few-shot learning of predicates.

Few-Shot Learning Graph Generation +4

HYPE: A Benchmark for Human eYe Perceptual Evaluation of Generative Models

no code implementations • NeurIPS 2019 • Sharon Zhou, Mitchell L. Gordon, Ranjay Krishna, Austin Narcomey, Li Fei-Fei, Michael S. Bernstein

We construct Human eYe Perceptual Evaluation (HYPE) a human benchmark that is (1) grounded in psychophysics research in perception, (2) reliable across different sets of randomly sampled outputs from a model, (3) able to produce separable model performances, and (4) efficient in cost and time.

Image Generation Unconditional Image Generation

HYPE: Human-eYe Perceptual Evaluation of Generative Models

no code implementations • ICLR Workshop DeepGenStruct 2019 • Sharon Zhou, Mitchell Gordon, Ranjay Krishna, Austin Narcomey, Durim Morina, Michael S. Bernstein

The second, HYPE-Infinity, measures human error rate on fake and real images with no time constraints, maintaining stability and drastically reducing time and cost.

Image Generation Unconditional Image Generation