Browse SoTA > Computer Vision > Object Detection > Zero-Shot Object Detection

Zero-Shot Object Detection

3 papers with code · Computer Vision
Subtask of Object Detection

Zero-shot object detection (ZSD) is the task of object detection where no visual training data is available for some of the target object classes.

( Image credit: Zero-Shot Object Detection: Learning to Simultaneously Recognize and Localize Novel Concepts )

Leaderboards

Greatest papers with code

Zero-Shot Object Detection: Learning to Simultaneously Recognize and Localize Novel Concepts

16 Mar 2018salman-h-khan/ZSD_Release

We hypothesize that this setting is ill-suited for real-world applications where unseen objects appear only as a part of a complex scene, warranting both the `recognition' and `localization' of an unseen category.

ZERO-SHOT LEARNING ZERO-SHOT OBJECT DETECTION

Polarity Loss for Zero-shot Object Detection

22 Nov 2018salman-h-khan/PL-ZSD_Release

This setting gives rise to the need for correct alignment between visual and semantic concepts, so that the unseen objects can be identified using only their semantic attributes.

METRIC LEARNING ZERO-SHOT LEARNING ZERO-SHOT OBJECT DETECTION

Zero-Shot Object Detection by Hybrid Region Embedding

16 May 2018berkandemirel/zero-shot-detection

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.

ZERO-SHOT OBJECT DETECTION