Abstract

Today’s state-of-the-art visual object detection systems are based on three key components: 1) sophisticated features (to encode various visual invariances), 2) a powerful classifier (to build a discriminative object class model), and 3) lots of data (to use in largescale hard-negative mining). While conventional wisdom tends to attribute the success of such methods to the ability of the classifier to generalize across the positive class instances, here we report on empirical findings suggesting that this might not necessarily be the case. We have experimented with a very simple idea: to learn a separate classifier for each positive object instance in the dataset (see Figure 1). In this setup, no generalization across the positive instances is possible by definition, and yet, surprisingly, we did not observe any drastic drop in performance compared to the standard, category-based approaches