Impostor Networks for Fast Fine-Grained Recognition
This work addresses the need for efficient fine-grained recognition on devices like CPUs, offering a solution that is particularly useful for applications on low-power and non-GPU enabled platforms, though it is incremental in its approach.
The paper tackles the problem of fine-grained recognition on low-power platforms by introducing impostor networks, which combine a lightweight convolutional network with a non-parametric classifier to achieve high accuracy with minimal computational cost, as demonstrated by boosting classification accuracy on three fine-grained datasets.
In this work we introduce impostor networks, an architecture that allows to perform fine-grained recognition with high accuracy and using a light-weight convolutional network, making it particularly suitable for fine-grained applications on low-power and non-GPU enabled platforms. Impostor networks compensate for the lightness of its `backend' network by combining it with a lightweight non-parametric classifier. The combination of a convolutional network and such non-parametric classifier is trained in an end-to-end fashion. Similarly to convolutional neural networks, impostor networks can fit large-scale training datasets very well, while also being able to generalize to new data points. At the same time, the bulk of computations within impostor networks happen through nearest neighbor search in high-dimensions. Such search can be performed efficiently on a variety of architectures including standard CPUs, where deep convolutional networks are inefficient. In a series of experiments with three fine-grained datasets, we show that impostor networks are able to boost the classification accuracy of a moderate-sized convolutional network considerably at a very small computational cost.