IRUS Total

Needles in haystacks: On classifying tiny objects in large images

File Description SizeFormat 
1908.06037v1.pdfWorking paper6.1 MBAdobe PDFView/Open
Title: Needles in haystacks: On classifying tiny objects in large images
Authors: Pawlowski, N
Bhooshan, S
Ballas, N
Ciompi, F
Glocker, B
Drozdzal, M
Item Type: Working Paper
Abstract: In some 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 and analyzed using biased datasets that contain large objects, most often, in 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 other from histopathology images. This testbed allows us to perform controlled experiments to stress-test CNN architectures using a broad spectrum of signal-to-noise ratios. Our observations suggest 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.
Issue Date: 16-Aug-2019
URI: http://hdl.handle.net/10044/1/73514
Publisher: arXiv
Copyright Statement: © 2019 The Author(s)
Keywords: cs.CV
Publication Status: Published
Appears in Collections:Computing