Training object class detectors from eye tracking data

Abstract. Training an object class detector typically requires a large set of im-ages annotated with bounding-boxes, which is expensive and time consuming to create. We propose novel approach to annotate object locations which can sub-stantially reduce annotation time. We first track the eye movements of annota-tors instructed to find the object and then propose a technique for deriving ob-ject bounding-boxes from these fixations. To validate our idea, we collected eye tracking data for the trainval part of 10 object classes of Pascal VOC 2012 (6,270 images, 5 observers). Our technique correctly produces bounding-boxes in 50% of the images, while reducing the total annotation time by factor 6.8 × compared to drawing bounding-boxes. Any standard object class detector can be trained on the bounding-boxes predicted by our model. Our large scale eye tracking dataset is available at groups.inf.ed.ac.uk/calvin/eyetrackdataset/.