One-shot Learning - Experimental Results - Motorbike Example

Motorbike Example

To learn the motorbike category:

• Six training images are selected from the motorbike category of the Caltech 4 Data Set and the Kadir Brady detector is applied, giving and through PCA, . Examples are shown below.

• Next, the prior model parameters are computed from 30 models, 10 from each of the three learnt categories: spotted cats, faces, and airplanes. This prior encodes the knowledge that "models lacking visual consistency occupy a different part of the parameter space coherent models."

• In learning, which is performed next, the prior biases the posterior towards parts of the parameter space corresponding to coherent models. Only one mixture component is used, letting . The estimation of the posterior is shown below.

• Finally, the figures below show the learned motorbike model with shape and appearance of parts, and the corresponding features.

• For recognition tests, the model above is applied to 50 images which contain motorbikes and 50 which do not. The image below shows an ROC curve, measuring the probability of detection over the probability of false detection, as well as some recognized examples.