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

6 Jan 2017  ·  Eshed Ohn-Bar, Mohan M. Trivedi ·

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.

PDF Abstract

Datasets


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Face Detection WIDER Face (Hard) LDCF+ AP 0.564 # 22
Face Detection WIDER Face (Medium) LDCF+ AP 0.772 # 18

Methods


No methods listed for this paper. Add relevant methods here