# Weakly Supervised Object Localization Using Size Estimates

arXiv: https://arxiv.org/abs/1608.04314 · HTML: https://mlsanity.com/paper/1608.04314/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Aug 2016.

## Built on by (most cited first, 16 of 16)

- [Curriculum Learning: A Survey](https://mlsanity.com/paper/2101.10382/) (2021)
- [Weakly Supervised Object Localization and Detection: A Survey](https://mlsanity.com/paper/2104.07918/) (2021)
- [Coaching a Teachable Student](https://mlsanity.com/paper/2306.10014/) (2023)
- [Boost Your Human Image Generation Model via Direct Preference Optimization](https://mlsanity.com/paper/2405.20216/) (2024)
- [ViTOL: Vision Transformer for Weakly Supervised Object Localization](https://mlsanity.com/paper/2204.06772/) (2022)
- [Intent-based Prompt Calibration: Enhancing prompt optimization with synthetic boundary cases](https://mlsanity.com/paper/2402.03099/) (2024)
- [Learning Rate Curriculum](https://mlsanity.com/paper/2205.09180/) (2022)
- [Reverse Stable Diffusion: What prompt was used to generate this image?](https://mlsanity.com/paper/2308.01472/) (2023)
- [A Realistic Protocol for Evaluation of Weakly Supervised Object Localization](https://mlsanity.com/paper/2404.10034/) (2024)
- [Disentangled Representation Learning for Controllable Person Image Generation](https://mlsanity.com/paper/2312.05798/) (2023)
- [Gyro-based Neural Single Image Deblurring](https://mlsanity.com/paper/2404.00916/) (2024)
- [CBM: Curriculum by Masking](https://mlsanity.com/paper/2407.05193/) (2024)
- [Weakly Supervised Foreground Learning for Weakly Supervised Localization and Detection](https://mlsanity.com/paper/2108.01785/) (2021)
- [Are Dense Labels Always Necessary for 3D Object Detection from Point Cloud?](https://mlsanity.com/paper/2403.02818/) (2024)
- [Contrastive Proposal Extension with LSTM Network for Weakly Supervised Object Detection](https://mlsanity.com/paper/2110.07511/) (2021)
- [Curriculum for Crowd Counting -- Is it Worthy?](https://mlsanity.com/paper/2401.07586/) (2024)

## Abstract (arXiv)

We present a technique for weakly supervised object localization (WSOL), building on the observation that WSOL algorithms usually work better on images with bigger objects. Instead of training the object detector on the entire training set at the same time, we propose a curriculum learning strategy to feed training images into the WSOL learning loop in an order from images containing bigger objects down to smaller ones. To automatically determine the order, we train a regressor to estimate the size of the object given the whole image as input. Furthermore, we use these size estimates to further improve the re-localization step of WSOL by assigning weights to object proposals according to how close their size matches the estimated object size. We demonstrate the effectiveness of using size order and size weighting on the challenging PASCAL VOC 2007 dataset, where we achieve a significant improvement over existing state-of-the-art WSOL techniques.