# What makes for effective detection proposals?

arXiv: https://arxiv.org/abs/1502.05082 · HTML: https://mlsanity.com/paper/1502.05082/

## Key facts

- Cited by 38 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Feb 2015.

## Built on by (most cited first, 30 of 38)

- [3D Object Detection for Autonomous Driving: A Survey](https://mlsanity.com/paper/2106.10823/) (2021)
- [DETReg: Unsupervised Pretraining with Region Priors for Object Detection](https://mlsanity.com/paper/2106.04550/) (2021)
- [FACET: Fairness in Computer Vision Evaluation Benchmark](https://mlsanity.com/paper/2309.00035/) (2023)
- [Meta Faster R-CNN: Towards Accurate Few-Shot Object Detection with Attentive Feature Alignment](https://mlsanity.com/paper/2104.07719/) (2021)
- [Instance Neural Radiance Field](https://mlsanity.com/paper/2304.04395/) (2023)
- [A Fully Spiking Hybrid Neural Network for Energy-Efficient Object Detection](https://mlsanity.com/paper/2104.10719/) (2021)
- [How stable are Transferability Metrics evaluations?](https://mlsanity.com/paper/2204.01403/) (2022)
- [Robust Double-Encoder Network for RGB-D Panoptic Segmentation](https://mlsanity.com/paper/2210.02834/) (2022)
- [Oriented object detection in optical remote sensing images using deep learning: a survey](https://mlsanity.com/paper/2302.10473/) (2023)
- [Scaling Novel Object Detection with Weakly Supervised Detection Transformers](https://mlsanity.com/paper/2207.05205/) (2022)
- [Iterative Next Boundary Detection for Instance Segmentation of Tree Rings in Microscopy Images of Shrub Cross Sections](https://mlsanity.com/paper/2212.03022/) (2022)
- [Meta-Point Learning and Refining for Category-Agnostic Pose Estimation](https://mlsanity.com/paper/2403.13647/) (2024)
- [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)
- [RETR: Multi-View Radar Detection Transformer for Indoor Perception](https://mlsanity.com/paper/2411.10293/) (2024)
- [Learning from Counting: Leveraging Temporal Classification for Weakly Supervised Object Localization and Detection](https://mlsanity.com/paper/2103.04009/) (2021)
- [Localizing Small Apples in Complex Apple Orchard Environments](https://mlsanity.com/paper/2202.11372/) (2022)
- [Superpixel-based Refinement for Object Proposal Generation](https://mlsanity.com/paper/2101.04574/) (2021)
- [Diagnosing Errors in Video Relation Detectors](https://mlsanity.com/paper/2110.13110/) (2021)
- [DeepFH Segmentations for Superpixel-based Object Proposal Refinement](https://mlsanity.com/paper/2108.03503/) (2021)
- [Tunable Hybrid Proposal Networks for the Open World](https://mlsanity.com/paper/2208.11050/) (2022)
- [LEDetection: A Simple Framework for Semi-Supervised Few-Shot Object Detection](https://mlsanity.com/paper/2303.05739/) (2023)
- [Finding Deviated Behaviors of the Compressed DNN Models for Image Classifications](https://mlsanity.com/paper/2112.02819/) (2021)
- [Learning High-quality Proposals for Acne Detection](https://mlsanity.com/paper/2207.03674/) (2022)
- [FashionFail: Addressing Failure Cases in Fashion Object Detection and Segmentation](https://mlsanity.com/paper/2404.08582/) (2024)
- [Weakly Supervised Panoptic Segmentation for Defect-Based Grading of Fresh Produce](https://mlsanity.com/paper/2411.16219/) (2024)
- [Tobler's First Law in GeoAI: A Spatially Explicit Deep Learning Model for Terrain Feature Detection Under Weak Supervision](https://mlsanity.com/paper/2508.03745/) (2025)
- [REXO: Indoor Multi-View Radar Object Detection via 3D Bounding Box Diffusion](https://mlsanity.com/paper/2511.17806/) (2025)
- [Segmenting Medical Instruments in Minimally Invasive Surgeries using AttentionMask](https://mlsanity.com/paper/2203.11358/) (2022)
- [N-RPN: Hard Example Learning for Region Proposal Networks](https://mlsanity.com/paper/2208.01916/) (2022)
- [Actor-identified Spatiotemporal Action Detection -- Detecting Who Is Doing What in Videos](https://mlsanity.com/paper/2208.12940/) (2022)

## Abstract (arXiv)

Current top performing object detectors employ detection proposals to guide the search for objects, thereby avoiding exhaustive sliding window search across images. Despite the popularity and widespread use of detection proposals, it is unclear which trade-offs are made when using them during object detection. We provide an in-depth analysis of twelve proposal methods along with four baselines regarding proposal repeatability, ground truth annotation recall on PASCAL, ImageNet, and MS COCO, and their impact on DPM, R-CNN, and Fast R-CNN detection performance. Our analysis shows that for object detection improving proposal localisation accuracy is as important as improving recall. We introduce a novel metric, the average recall (AR), which rewards both high recall and good localisation and correlates surprisingly well with detection performance. Our findings show common strengths and weaknesses of existing methods, and provide insights and metrics for selecting and tuning proposal methods.