Zero-Shot Object Detection by Hybrid Region Embedding
This addresses the problem of detecting objects without visual training data for some classes, which is an incremental advancement in computer vision.
The paper tackles zero-shot object detection (ZSD) by proposing a novel approach using hybrid region embeddings, achieving promising results on custom datasets derived from Fashion-MNIST and Pascal VOC.
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.