papers AI Learner
The Github is limit! Click to go to the new site.

Thinking Outside the Pool: Active Training Image Creation for Relative Attributes

2019-01-08
Aron Yu, Kristen Grauman

Abstract

Current wisdom suggests more labeled image data is always better, and obtaining labels is the bottleneck. Yet curating a pool of sufficiently diverse and informative images is itself a challenge. In particular, training image curation is problematic for fine-grained attributes, where the subtle visual differences of interest may be rare within traditional image sources. We propose an active image generation approach to address this issue. The main idea is to jointly learn the attribute ranking task while also learning to generate novel realistic image samples that will benefit that task. We introduce an end-to-end framework that dynamically “imagines” image pairs that would confuse the current model, presents them to human annotators for labeling, then improves the predictive model with the new examples. With results on two datasets, we show that by thinking outside the pool of real images, our approach gains generalization accuracy for challenging fine-grained attribute comparisons.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1901.02551

PDF

http://arxiv.org/pdf/1901.02551


Similar Posts

Comments