# Deep Descriptor Transforming for Image Co-Localization

arXiv: https://arxiv.org/abs/1705.02758 · HTML: https://mlsanity.com/paper/1705.02758/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 May 2017.

## Built on by (most cited first, 6 of 6)

- [Weakly Supervised Object Localization and Detection: A Survey](https://mlsanity.com/paper/2104.07918/) (2021)
- [Large-Scale Unsupervised Object Discovery](https://mlsanity.com/paper/2106.06650/) (2021)
- [Image Segmentation-based Unsupervised Multiple Objects Discovery](https://mlsanity.com/paper/2212.10124/) (2022)
- [Learning Transferable Reward for Query Object Localization with Policy Adaptation](https://mlsanity.com/paper/2202.12403/) (2022)
- [Automatic Bounding Box Annotation with Small Training Data Sets for Industrial Manufacturing](https://mlsanity.com/paper/2206.00280/) (2022)
- [Latent Commonality Expectation-Maximisation for Box-supervised Tree Crown Instance Segmentation](https://mlsanity.com/paper/2609.26549/) (2026)

## Abstract (arXiv)

Reusable model design becomes desirable with the rapid expansion of machine learning applications. In this paper, we focus on the reusability of pre-trained deep convolutional models. Specifically, different from treating pre-trained models as feature extractors, we reveal more treasures beneath convolutional layers, i.e., the convolutional activations could act as a detector for the common object in the image co-localization problem. We propose a simple but effective method, named Deep Descriptor Transforming (DDT), for evaluating the correlations of descriptors and then obtaining the category-consistent regions, which can accurately locate the common object in a set of images. Empirical studies validate the effectiveness of the proposed DDT method. On benchmark image co-localization datasets, DDT consistently outperforms existing state-of-the-art methods by a large margin. Moreover, DDT also demonstrates good generalization ability for unseen categories and robustness for dealing with noisy data.