English

ASOC: Adaptive Self-aware Object Co-localization

Computer Vision and Pattern Recognition 2022-02-17 v1 Multimedia Image and Video Processing

Abstract

The primary goal of this paper is to localize objects in a group of semantically similar images jointly, also known as the object co-localization problem. Most related existing works are essentially weakly-supervised, relying prominently on the neighboring images' weak-supervision. Although weak supervision is beneficial, it is not entirely reliable, for the results are quite sensitive to the neighboring images considered. In this paper, we combine it with a self-awareness phenomenon to mitigate this issue. By self-awareness here, we refer to the solution derived from the image itself in the form of saliency cue, which can also be unreliable if applied alone. Nevertheless, combining these two paradigms together can lead to a better co-localization ability. Specifically, we introduce a dynamic mediator that adaptively strikes a proper balance between the two static solutions to provide an optimal solution. Therefore, we call this method \textit{ASOC}: Adaptive Self-aware Object Co-localization. We perform exhaustive experiments on several benchmark datasets and validate that weak-supervision supplemented with self-awareness has superior performance outperforming several compared competing methods.

Keywords

Cite

@article{arxiv.2201.11547,
  title  = {ASOC: Adaptive Self-aware Object Co-localization},
  author = {Koteswar Rao Jerripothula and Prerana Mukherjee},
  journal= {arXiv preprint arXiv:2201.11547},
  year   = {2022}
}

Comments

Published in IEEE ICME 2021. Please cite this paper in the following manner: K. R. Jerripothula and P. Mukherjee, "ASOC: Adaptive Self-Aware Object Co-Localization," 2021 IEEE International Conference on Multimedia and Expo (ICME), 2021, pp. 1-6, doi: 10.1109/ICME51207.2021.9428191

R2 v1 2026-06-24T09:05:33.585Z