# To Boost or Not to Boost? On the Limits of Boosted Trees for Object Detection

arXiv: https://arxiv.org/abs/1701.01692 · HTML: https://mlsanity.com/paper/1701.01692/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Jan 2017.

## Built on by (most cited first, 4 of 4)

- [LDC-Net: A Unified Framework for Localization, Detection and Counting in Dense Crowds](https://mlsanity.com/paper/2110.04727/) (2021)
- [Wide Aspect Ratio Matching for Robust Face Detection](https://mlsanity.com/paper/2103.05993/) (2021)
- [Which to Match? Selecting Consistent GT-Proposal Assignment for Pedestrian Detection](https://mlsanity.com/paper/2103.10091/) (2021)
- [Bounding-box deep calibration for high performance face detection](https://mlsanity.com/paper/2110.03892/) (2021)

## Abstract (arXiv)

We aim to study the modeling limitations of the commonly employed boosted decision trees classifier. Inspired by the success of large, data-hungry visual recognition models (e.g. deep convolutional neural networks), this paper focuses on the relationship between modeling capacity of the weak learners, dataset size, and dataset properties. A set of novel experiments on the Caltech Pedestrian Detection benchmark results in the best known performance among non-CNN techniques while operating at fast run-time speed. Furthermore, the performance is on par with deep architectures (9.71% log-average miss rate), while using only HOG+LUV channels as features. The conclusions from this study are shown to generalize over different object detection domains as demonstrated on the FDDB face detection benchmark (93.37% accuracy). Despite the impressive performance, this study reveals the limited modeling capacity of the common boosted trees model, motivating a need for architectural changes in order to compete with multi-level and very deep architectures.