{
  "id": "1701.01692",
  "version": "v1",
  "published": "2017-01-06T16:51:32.000Z",
  "updated": "2017-01-06T16:51:32.000Z",
  "title": "To Boost or Not to Boost? On the Limits of Boosted Trees for Object Detection",
  "authors": [
    "Eshed Ohn-Bar",
    "Mohan M. Trivedi"
  ],
  "comment": "ICPR, December 2016. Added WIDER FACE test results (Fig. 5)",
  "categories": [
    "cs.CV"
  ],
  "abstract": "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.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2017-01-06T16:51:32.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "object detection",
      "boosted trees",
      "boosted decision trees classifier",
      "employed boosted decision trees",
      "caltech pedestrian detection benchmark results"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}