# ASOC: Adaptive Self-aware Object Co-localization

arXiv: https://arxiv.org/abs/2201.11547 · HTML: https://mlsanity.com/paper/2201.11547/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 10 of its 26 references that are in the map.
- First posted on arXiv 27 Jan 2022.

## Builds on (most cited first, 10 of 10)

- [Unsupervised Object Discovery and Localization in the Wild: Part-based Matching with Bottom-up Region Proposals](https://mlsanity.com/paper/1501.06170/) (2015)
- [Toward unsupervised, multi-object discovery in large-scale image collections](https://mlsanity.com/paper/2007.02662/) (2020)
- [Selective Convolutional Descriptor Aggregation for Fine-Grained Image Retrieval](https://mlsanity.com/paper/1604.04994/) (2016)
- [Deep Object Co-Segmentation](https://mlsanity.com/paper/1804.06423/) (2018)
- [Unsupervised Object Discovery and Co-Localization by Deep Descriptor Transforming](https://mlsanity.com/paper/1707.06397/) (2017)
- [Semantic Aware Attention Based Deep Object Co-segmentation](https://mlsanity.com/paper/1810.06859/) (2018)
- [Image Co-localization by Mimicking a Good Detector's Confidence Score Distribution](https://mlsanity.com/paper/1603.04619/) (2016)
- [Iterative Spectral Clustering for Unsupervised Object Localization](https://mlsanity.com/paper/1706.09719/) (2017)
- [Image Co-skeletonization via Co-segmentation](https://mlsanity.com/paper/2004.05575/) (2020)
- [Associative embeddings for large-scale knowledge transfer with self-assessment](https://mlsanity.com/paper/1312.3240/) (2013)

## Abstract (arXiv)

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 textitASOC: 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.