Learning to Focus Attention on Discriminative Regions for Object Detection

A major task of visual attention is to focus processing on regions of interest to enable rapid and robust object search. Instead of integrating generic feature extraction into object specific interpretation we strictly pursue a top-down approach. Early features are tuned to selectively respond to task related visual features, i.e., locally discriminative information that is useful in object recognition. In this work we determine discriminative regions from the information content in the local appearance patterns. A rapid mapping from appearances to discriminative regions is estimated using decision trees. The focus of attention on discriminative patterns enables then efficient detection of a searched object, but also the definition of sparse object representations to respond only to task relevant information. In the experiments, the performance in object recognition from single imagettes dramatically increased considering only discriminative patterns. Evaluation of complete image analysis under various degrees of partial occlusion and image noise resulted in highly robust recognition even in the presence of severe occlusion and noise effects. Finally, preliminary results on attentive object detection in cluttered environments demonstrated successful indexing to relevant locations.