We present log-linear mixture models as a fully discriminative approach to object category recognition which can, analogously to kernelised models, represent non-linear decision boundaries. We show that this model is the discriminative counterpart to Gaussian mixtures and that either one can be transformed into the respective other. However, the proposed model is easier to extend toward fusing multiple cues and numerically more stable to train and to evaluate. Experiments on the PASCAL VOC 2006 data show that the performance of our model compares favourably well to the state-of-the-art despite the model consisting of an order of magnitude fewer parameters, which suggests excellent generalisation capabilities. 1

We present a new technique that employs support vector machines (SVMs) and Gaussian mixture densities (GMDs) to create a generative/discriminative object classification technique using local image features. In the past, several approaches to fuse the advantages of generative and discriminative approaches were presented, often leading to improved robustness and recognition accuracy. Support vector machines are a well known discriminative classification framework but, similar to other discriminative approaches, suffer from a lack of robustness with respect to noise and overfitting. Gaussian mixtures, on the contrary, are a widely used generative technique. We present a method to directly fuse both approaches, effectively allowing to fully exploit the advantages of both. The fusion of SVMs and GMDs is done by representing SVMs in the framework of GMDs without changing the training and without changing the decision boundary. The new classifier is evaluated on the PASCAL VOC 2006 data. Additionally, we perform experiments on the USPS dataset and on four tasks from the UCI machine learning repository to obtain additional insights into the properties of the proposed approach. It is shown that for the relatively rare cases where SVMs have problems, the combined method outperforms both individual ones.

Witnessing the sheer amount of user-contributed photos and videos, we argue to leverage such freely available image collections as the training images for image classification. We propose an image expansion framework to mine more semantically related training images from the auxiliary image collection provided very few training examples. The expansion is based on a semantic graph considering both visual and (noisy) textual similarities in the auxiliary image collections, where we also consider scalability issues (e.g., MapReduce) as constructing the graph. We found the expanded images not only reduce the time-consuming (manual) annotation efforts but also further improve the classification accuracy since more visually diverse training images are included. Experimenting in certain benchmarks, we show that the expanded training images improve image classification significantly. Furthermore, we achieve more than 27 % relative improvement in accuracy compared to the state-of-the-art training image crowdsourcing approaches by exploiting media sharing services (such as Flickr) for additional training images.