Needles in Haystacks: On Classifying Tiny Objects in Large Images

by   Nick Pawlowski, et al.

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.


page 2

page 6

page 8

page 14

page 17

page 20

page 21


Inference on Achieved Signal Noise Ratio

We describe a procedure to perform approximate inference on the achieved...

Efficient Classification of Very Large Images with Tiny Objects

An increasing number of applications in the computer vision domain, spec...

Examining convolutional feature extraction using Maximum Entropy (ME) and Signal-to-Noise Ratio (SNR) for image classification

Convolutional Neural Networks (CNNs) specialize in feature extraction ra...

Efficient feature learning and multi-size image steganalysis based on CNN

For steganalysis, many studies showed that convolutional neural network ...

A study on the deviations in performance of FNNs and CNNs in the realm of grayscale adversarial images

Neural Networks are prone to having lesser accuracy in the classificatio...

AeroRIT: A New Scene for Hyperspectral Image Analysis

Hyperspectral imagery oriented research like image super-resolution and ...

The Benefit of Distraction: Denoising Remote Vitals Measurements using Inverse Attention

Attention is a powerful concept in computer vision. End-to-end networks ...

Please sign up or login with your details

Forgot password? Click here to reset