Context Forest for efficient object detection with large mixture models
This addresses efficiency issues in object detection for applications using large datasets, though it is incremental as it builds on existing detector frameworks.
The paper tackles the problem of speeding up multi-component object detectors by introducing Context Forest (ConF), a technique that predicts object properties from global image appearance to select relevant detector components, resulting in speed-ups of 2x for DPM and 10x for EE-SVM detectors, and improving mAP by about 2% by reducing false positives.
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 train ConF to predict which aspects of an object class are likely to appear in a given image (e.g. which viewpoint). This enables to speed-up multi-component object detectors, by automatically selecting the most relevant components to run on that image. This is particularly useful for detectors trained from large datasets, which typically need many components to fully absorb the data and reach their peak performance. ConF provides a speed-up of 2x for the DPM detector [1] and of 10x for the EE-SVM detector [2]. To show ConF's generality, we also train it to predict at which locations objects are likely to appear in an image. Incorporating this information in the detector score improves mAP performance by about 2% by removing false positive detections in unlikely locations.