A Multi-Space Approach to Zero-Shot Object Detection

Gupta, Dikshant and Anantharaman, Aditya and Mamgain, Nehal and S, Sowmya Kamath and Balasubramanian, Vineeth N and Jawahar, C.V. (2020) A Multi-Space Approach to Zero-Shot Object Detection. In: Proceedings - 2020 IEEE Winter Conference on Applications of Computer Vision, WACV 2020, 1 March 2020 - 5 March 2020.

Full text not available from this repository. (Request a copy)


Object detection has been at the forefront for higher level vision tasks such as scene understanding and contextual reasoning. Therefore, solving object detection for a large number of visual categories is paramount. Zero-Shot Object Detection (ZSD) - where training data is not available for some of the target classes - provides semantic scalability to object detection and reduces dependence on large amount of annotations, thus enabling a large number of applications in real-life scenarios. In this paper, we propose a novel multi-space approach to solve ZSD where we combine predictions obtained in two different search spaces. We learn the projection of visual features of proposals to the semantic embedding space and class labels in the semantic embedding space to visual space. We predict similarity scores in the individual spaces and combine them. We present promising results on two datasets, PASCAL VOC and MS COCO. We further discuss the problem of hubness and show that our approach alleviates hubness with a performance superior to previously proposed methods.

[error in script]
IITH Creators:
IITH CreatorsORCiD
Gupta, DikshantUNSPECIFIED
Balasubramanian, Vineeth NUNSPECIFIED
Item Type: Conference or Workshop Item (Paper)
Uncontrolled Keywords: Contextual reasoning; Large amounts; Scene understanding; Search spaces; Semantic embedding; Similarity scores; Training data; Visual feature
Subjects: Computer science
Divisions: Department of Computer Science & Engineering
Depositing User: . LibTrainee 2021
Date Deposited: 31 Jul 2021 11:27
Last Modified: 31 Jul 2021 11:27
URI: http://raiith.iith.ac.in/id/eprint/8613
Publisher URL: http://doi.org/10.1109/WACV45572.2020.9093384
Related URLs:

Actions (login required)

View Item View Item
Statistics for RAIITH ePrint 8613 Statistics for this ePrint Item