# Adaptively Denoising Proposal Collection for Weakly Supervised Object Localization

arXiv: https://arxiv.org/abs/1910.02101 · HTML: https://mlsanity.com/paper/1910.02101/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Oct 2019.

## Built on by (most cited first, 9 of 9)

- [Weakly Supervised Object Localization and Detection: A Survey](https://mlsanity.com/paper/2104.07918/) (2021)
- [Colonoscopy Polyp Detection and Classification: Dataset Creation and Comparative Evaluations](https://mlsanity.com/paper/2104.10824/) (2021)
- [Enhanced U-Net: A Feature Enhancement Network for Polyp Segmentation](https://mlsanity.com/paper/2105.00999/) (2021)
- [A Fine-Grained Visual Attention Approach for Fingerspelling Recognition in the Wild](https://mlsanity.com/paper/2105.07625/) (2021)
- [A Domain Gap Aware Generative Adversarial Network for Multi-domain Image Translation](https://mlsanity.com/paper/2110.10837/) (2021)
- [Dynamic Label Assignment for Object Detection by Combining Predicted IoUs and Anchor IoUs](https://mlsanity.com/paper/2201.09396/) (2022)
- [MOFA: A Model Simplification Roadmap for Image Restoration on Mobile Devices](https://mlsanity.com/paper/2308.12494/) (2023)
- [Disentangled Representation Learning for Controllable Person Image Generation](https://mlsanity.com/paper/2312.05798/) (2023)
- [Multiple Classifiers Based Maximum Classifier Discrepancy for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2108.00610/) (2021)

## Abstract (arXiv)

In this paper, we address the problem of weakly supervised object localization (WSL), which trains a detection network on the dataset with only image-level annotations. The proposed approach is built on the observation that the proposal set from the training dataset is a collection of background, object parts, and objects. Several strategies are taken to adaptively eliminate the noisy proposals and generate pseudo object-level annotations for the weakly labeled dataset. A multiple instance learning (MIL) algorithm enhanced by mask-out strategy is adopted to collect the class-specific object proposals, which are then utilized to adapt a pre-trained classification network to a detection network. In addition, the detection results from the detection network are re-weighted by jointly considering the detection scores and the overlap ratio of proposals in a proposal subset optimization framework. The optimal proposals work as object-level labels that enable a pseudo-strongly supervised dataset for training the detection network. Consequently, we establish a fully adaptive detection network. Extensive evaluations on the PASCAL VOC 2007 and 2012 datasets demonstrate a significant improvement compared with the state-of-the-art methods.