Needles in Haystacks: On Classifying Tiny Objects in Large Images
This addresses a critical issue in domains like medical or hyperspectral imaging, but is incremental as it builds on existing CNN architectures with controlled experiments.
The study tackled the problem of classifying tiny objects in large images, finding that CNNs fail to generalize below a certain signal-to-noise limit, with required training data scaling rapidly with the inverse of object-to-image ratio, and that higher capacity models and adapted receptive fields improve performance.
In some important computer vision domains, such as medical or hyperspectral imaging, we care about the classification of tiny objects in large images. However, most Convolutional Neural Networks (CNNs) for image classification were developed using biased datasets that contain large objects, in mostly central image positions. To assess whether classical CNN architectures work well for tiny object classification we build a comprehensive testbed containing two datasets: one derived from MNIST digits and one from histopathology images. This testbed allows controlled experiments to stress-test CNN architectures with a broad spectrum of signal-to-noise ratios. Our observations indicate that: (1) There exists a limit to signal-to-noise below which CNNs fail to generalize and that this limit is affected by dataset size - more data leading to better performances; however, the amount of training data required for the model to generalize scales rapidly with the inverse of the object-to-image ratio (2) in general, higher capacity models exhibit better generalization; (3) when knowing the approximate object sizes, adapting receptive field is beneficial; and (4) for very small signal-to-noise ratio the choice of global pooling operation affects optimization, whereas for relatively large signal-to-noise values, all tested global pooling operations exhibit similar performance.