# Scalable, High-Quality Object Detection

arXiv: https://arxiv.org/abs/1412.1441 · HTML: https://mlsanity.com/paper/1412.1441/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Dec 2014.

## Built on by (most cited first, 11 of 11)

- [Cascade-DETR: Delving into High-Quality Universal Object Detection](https://mlsanity.com/paper/2307.11035/) (2023)
- [Spatio-Temporal Interaction Graph Parsing Networks for Human-Object Interaction Recognition](https://mlsanity.com/paper/2108.08633/) (2021)
- [Benchmarking Object Detectors under Real-World Distribution Shifts in Satellite Imagery](https://mlsanity.com/paper/2503.19202/) (2025)
- [Directly Optimizing IoU for Bounding Box Localization](https://mlsanity.com/paper/2304.07256/) (2023)
- [Fused Deep Neural Network based Transfer Learning in Occluded Face Classification and Person re-Identification](https://mlsanity.com/paper/2205.07203/) (2022)
- [Robot to Human Object Handover using Vision and Joint Torque Sensor Modalities](https://mlsanity.com/paper/2210.15085/) (2022)
- [ResNLS: An Improved Model for Stock Price Forecasting](https://mlsanity.com/paper/2312.01020/) (2023)
- [Damage GAN: A Generative Model for Imbalanced Data](https://mlsanity.com/paper/2312.04862/) (2023)
- [Improving Detection of Person Class Using Dense Pooling](https://mlsanity.com/paper/2410.20966/) (2024)
- [Region-Aware Deformable Convolutions](https://mlsanity.com/paper/2509.15436/) (2025)
- [Adaptive Multi-Scale Goodness Aggregation for Forward-Forward Learning](https://mlsanity.com/paper/2605.18804/) (2026)

## Abstract (arXiv)

Current high-quality object detection approaches use the scheme of salience-based object proposal methods followed by post-classification using deep convolutional features. This spurred recent research in improving object proposal methods. However, domain agnostic proposal generation has the principal drawback that the proposals come unranked or with very weak ranking, making it hard to trade-off quality for running time. This raises the more fundamental question of whether high-quality proposal generation requires careful engineering or can be derived just from data alone. We demonstrate that learning-based proposal methods can effectively match the performance of hand-engineered methods while allowing for very efficient runtime-quality trade-offs. Using the multi-scale convolutional MultiBox (MSC-MultiBox) approach, we substantially advance the state-of-the-art on the ILSVRC 2014 detection challenge data set, with 0.5 mAP for a single model and 0.52 mAP for an ensemble of two models. MSC-Multibox significantly improves the proposal quality over its predecessor MultiBox~method: AP increases from 0.42 to 0.53 for the ILSVRC detection challenge. Finally, we demonstrate improved bounding-box recall compared to Multiscale Combinatorial Grouping with less proposals on the Microsoft-COCO data set.