Context Forest for object class detection

Davide Modolo, Alexander Vezhnevets, Vittorio Ferrari

Research output: Chapter in Book/Report/Conference proceedingConference contribution


We present Context Forest (ConF) — a technique for predicting properties of the objects in an image based on its global appearance. Compared to standard nearest- neighbour techniques, ConF is more accurate, fast and memory efficient. We demonstrate ConF by predicting three properties: aspects of appearance, location in the image, and class membership. In extensive experiments we show that (i) ConF can automatically select which components of a multi-component detector to run on a given test image, obtaining a considerable speed-up for detectors trained from large sets (10 for EE-SVMs [36] and 2 for DPM [21]); (ii) ConF can improve object detection performance by removing false positive detections at unlikely locations (+2% mAP), and by (iii) removing false positives produced by classes unlikely to be present in the image (+5% mAP on a 200-class dataset [2])
Original languageEnglish
Title of host publicationBritish Machine Vision Conference 2015
Number of pages14
Publication statusPublished - Sep 2015


Dive into the research topics of 'Context Forest for object class detection'. Together they form a unique fingerprint.

Cite this