Locally Scale-Invariant Convolutional Neural Networks
This work addresses the problem of improving ConvNet robustness to scale changes for computer vision tasks, but it is incremental as it builds on existing invariance learning approaches.
The paper tackles the challenge of scale variation in visual classification by proposing a locally scale-invariant convolutional neural network that learns more discriminative features with reduced over-fitting, as demonstrated on a modified MNIST dataset.
Convolutional Neural Networks (ConvNets) have shown excellent results on many visual classification tasks. With the exception of ImageNet, these datasets are carefully crafted such that objects are well-aligned at similar scales. Naturally, the feature learning problem gets more challenging as the amount of variation in the data increases, as the models have to learn to be invariant to certain changes in appearance. Recent results on the ImageNet dataset show that given enough data, ConvNets can learn such invariances producing very discriminative features [1]. But could we do more: use less parameters, less data, learn more discriminative features, if certain invariances were built into the learning process? In this paper we present a simple model that allows ConvNets to learn features in a locally scale-invariant manner without increasing the number of model parameters. We show on a modified MNIST dataset that when faced with scale variation, building in scale-invariance allows ConvNets to learn more discriminative features with reduced chances of over-fitting.