# How good are detection proposals, really?

arXiv: https://arxiv.org/abs/1406.6962 · HTML: https://mlsanity.com/paper/1406.6962/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Jun 2014.

## Built on by (most cited first, 7 of 7)

- [DETReg: Unsupervised Pretraining with Region Priors for Object Detection](https://mlsanity.com/paper/2106.04550/) (2021)
- [Rethinking Few-Shot Object Detection on a Multi-Domain Benchmark](https://mlsanity.com/paper/2207.11169/) (2022)
- [Postdisaster image-based damage detection and repair cost estimation of reinforced concrete buildings using dual convolutional neural networks](https://mlsanity.com/paper/2111.09862/) (2021)
- [A Realistic Protocol for Evaluation of Weakly Supervised Object Localization](https://mlsanity.com/paper/2404.10034/) (2024)
- [Diagnosing Errors in Video Relation Detectors](https://mlsanity.com/paper/2110.13110/) (2021)
- [Modeling long-term interactions to enhance action recognition](https://mlsanity.com/paper/2104.11520/) (2021)
- [Improving Detection of Person Class Using Dense Pooling](https://mlsanity.com/paper/2410.20966/) (2024)

## Abstract (arXiv)

Current top performing Pascal VOC object detectors employ detection proposals to guide the search for objects thereby avoiding exhaustive sliding window search across images. Despite the popularity of detection proposals, it is unclear which trade-offs are made when using them during object detection. We provide an in depth analysis of ten object proposal methods along with four baselines regarding ground truth annotation recall (on Pascal VOC 2007 and ImageNet 2013), repeatability, and impact on DPM detector performance. Our findings show common weaknesses of existing methods, and provide insights to choose the most adequate method for different settings.