CVMMIVJan 27, 2022

ASOC: Adaptive Self-aware Object Co-localization

arXiv:2201.11547v1
AI Analysis

This work addresses the sensitivity of weak supervision in object co-localization for computer vision applications, offering an incremental improvement.

The paper tackles the object co-localization problem by combining weak supervision from neighboring images with self-awareness from saliency cues, using a dynamic mediator to balance them, resulting in superior performance on benchmark datasets.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes