APSIPA Transactions on Signal and Information Processing > Vol 11 > Issue 1

Bridging Gap between Image Pixels and Semantics via Supervision: A Survey

Jiali Duan, University of Southern California, USA, jialidua@usc.edu , C.-C. Jay Kuo, University of Southern California, USA
Suggested Citation
Jiali Duan and C.-C. Jay Kuo (2022), "Bridging Gap between Image Pixels and Semantics via Supervision: A Survey", APSIPA Transactions on Signal and Information Processing: Vol. 11: No. 1, e2. http://dx.doi.org/10.1561/116.00000038

Publication Date: 24 Feb 2022
© 2022 J. Duan, C.C. J. Kuo
Semantic GapSemantic UnderstandingContent-based Image RetrievalSupervisionObject DetectionMetric Learning


Open Access

This is published under the terms of CC BY-NC.

Downloaded: 1898 times

In this article:
Background Review 
Supervision for Object Detection 
Supervision for Metric Learning 
Future Research Directions 


The fact that there exists a gap between low-level features and semantic meanings of images, called the semantic gap, is known for decades. Resolution of the semantic gap is a long standing problem. The semantic gap problem is reviewed and a survey on recent efforts in bridging the gap is made in this work. Most importantly, we claim that the semantic gap is primarily bridged through supervised learning today. Experiences are drawn from two application domains to illustrate this point: (1) object detection and (2) metric learning for content-based image retrieval (CBIR). To begin with, this paper offers a historical retrospective on supervision, makes a gradual transition to the modern data-driven methodology and introduces commonly used datasets. Then, it summarizes various supervision methods to bridge the semantic gap in the context of object detection and metric learning.



APSIPA Transactions on Signal and Information Processing Deep Neural Networks: Representation, Interpretation, and Applications: Articles Overview
See the other articles that are part of this special issue.