Synthesizing the Unseen for Zero-shot Object Detection

Cited by: 0|Bibtex|Views2|Links

Abstract:

The existing zero-shot detection approaches project visual features to the semantic domain for seen objects, hoping to map unseen objects to their corresponding semantics during inference. However, since the unseen objects are never visualized during training, the detection model is skewed towards seen content, thereby labeling unseen a...More

Code:

Data:

Your rating :
0

 

Tags
Comments