ASOC: Adaptive Self-aware Object Co-localization

TL;DR

This paper introduces ASOC, a method that combines weak supervision with self-awareness via saliency cues, using a dynamic mediator to improve object co-localization in images.

Contribution

It proposes a novel adaptive framework that balances weak supervision and self-awareness for more accurate object co-localization.

Findings

Outperforms several competing methods on benchmark datasets.

Demonstrates robustness by combining weak supervision with self-awareness.

Achieves superior localization accuracy through adaptive balancing.

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.