Needles in Haystacks: On Classifying Tiny Objects in Large Images

Abstract

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.

References in corpus (11)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Instance Normalization: The Missing Ingredient for Fast Stylization
• Validation, comparison, and combination of algorithms for automatic detection of pulmonary nodules in computed tomography images: the LUNA16 challenge
• Recurrent Models of Visual Attention
• Attention-based Deep Multiple Instance Learning
• MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labels
• A Closer Look at Memorization in Deep Networks
• Sensitivity and Generalization in Neural Networks: an Empirical Study
• Three Factors Influencing Minima in SGD
• Approximating CNNs with Bag-of-local-Features models works surprisingly well on ImageNet
• 3D multirater RCNN for multimodal multiclass detection and characterisation of extremely small objects

Cited by in corpus (4)

• Extending Unsupervised Neural Image Compression With Supervised Multitask Learning
• Quantum Tensor Network in Machine Learning: An Application to Tiny Object Classification
• Do We Need Fully Connected Output Layers in Convolutional Networks?
• Efficient Classification of Very Large Images with Tiny Objects