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

Zero-Shot Object Detection by Hybrid Region Embedding

2018-05-17
Berkan Demirel, Ramazan Gokberk Cinbis, Nazli Ikizler-Cinbis

Abstract

Object detection is considered as one of the most challenging problems in computer vision, since it requires correct prediction of both classes and locations of objects in images. In this study, we define a more difficult scenario, namely zero-shot object detection (ZSD) where no visual training data is available for some of the target object classes. We present a novel approach to tackle this ZSD problem, where a convex combination of embeddings are used in conjunction with a detection framework. For evaluation of ZSD methods, we propose a simple dataset constructed from Fashion-MNIST images and also a custom zero-shot split for the Pascal VOC detection challenge. The experimental results suggest that our method yields promising results for ZSD.

Abstract (translated by Google)
URL

https://arxiv.org/abs/1805.06157

PDF

https://arxiv.org/pdf/1805.06157


Similar Posts

Comments