Local Feature Descriptor Learning with Adaptive Siamese Network
This work addresses a specific bottleneck in local feature descriptor learning for computer vision applications, offering an incremental improvement over existing methods.
The paper tackles the problem of determining the optimal neural network size for learning local feature descriptors by introducing an adaptive pruning Siamese architecture based on neuron activation, resulting in improved computational efficiency and recognition rates that outperform state-of-the-art methods in patch matching.
Although the recent progress in the deep neural network has led to the development of learnable local feature descriptors, there is no explicit answer for estimation of the necessary size of a neural network. Specifically, the local feature is represented in a low dimensional space, so the neural network should have more compact structure. The small networks required for local feature descriptor learning may be sensitive to initial conditions and learning parameters and more likely to become trapped in local minima. In order to address the above problem, we introduce an adaptive pruning Siamese Architecture based on neuron activation to learn local feature descriptors, making the network more computationally efficient with an improved recognition rate over more complex networks. Our experiments demonstrate that our learned local feature descriptors outperform the state-of-art methods in patch matching.