The Vigilance Increment: An Ideal Observer Hypothesis

This work reports on convolutional neural network (CNN) performance on an image texture classification task as a function of linear image processing and number of training images. Detection performance of single and multi-layer CNNs (sCNN/mCNN) are compared to optimal observers. Performance is quantified by the area under the receiver operating characteristic (ROC) curve, also known as the AUC. For perfect detection AUC = 1.0 and AUC = 0.5 for guessing. The Ideal Observer (IO) maximizes AUC but is prohibitive in practice because it depends on high-dimensional image likelihoods. The IO performance is invariant to any fullrank, invertible linear image processing. This work demonstrates the existence of full-rank, invertible linear transforms that can degrade both sCNN and mCNN even in the limit of large quantities of training data. A subsequent invertible linear transform changes the images’ correlation structure again and can improve this AUC. Stationary textures sampled from zero mean and unequal covariance Gaussian distributions allow closed-form analytic expressions for the IO and optimal linear compression. Linear compression is a mitigation technique for high-dimension low sample size (HDLSS) applications. By definition, compression strictly decreases or maintains IO detection performance. For small quantities of training data, linear image compression prior to the sCNN architecture can increase AUC from 0.56 to 0.93. Results indicate an optimal compression ratio for CNN based on task difficulty, compression method, and number of training images.

Download Full-text

Object Detection Using an Ideal Observer Model

Electronic Imaging ◽

10.2352/issn.2470-1173.2020.16.avm-041 ◽

2020 ◽

Vol 2020 (16) ◽

pp. 41-1-41-7

Author(s):

Orit Skorka ◽

Paul J. Kane

Keyword(s):

Object Detection ◽

Matched Filter ◽

Image Sensors ◽

Ideal Observer ◽

Noise Power ◽

Relative Evaluation ◽

Detection And Identification ◽

Cross Correlation Analysis ◽

Observer Model ◽

The Ideal

Many of the metrics developed for informational imaging are useful in automotive imaging, since many of the tasks – for example, object detection and identification – are similar. This work discusses sensor characterization parameters for the Ideal Observer SNR model, and elaborates on the noise power spectrum. It presents cross-correlation analysis results for matched-filter detection of a tribar pattern in sets of resolution target images that were captured with three image sensors over a range of illumination levels. Lastly, the work compares the crosscorrelation data to predictions made by the Ideal Observer Model and demonstrates good agreement between the two methods on relative evaluation of detection capabilities.

Download Full-text

A Defense of Modest Ideal Observer Theory: The Case of Adam Smith’s Impartial Spectator

Ethical Theory and Moral Practice ◽

10.1007/s10677-021-10187-3 ◽

2021 ◽

Author(s):

Nir Ben-Moshe

Keyword(s):

Ideal Observer ◽

Impartial Spectator

Download Full-text

Image quality, the ideal observer, and human performance of radiologic decision tasks

Academic Radiology ◽

10.1016/s1076-6332(05)80411-8 ◽

1995 ◽

Vol 2 (6) ◽

pp. 522-526 ◽

Cited By ~ 27

Author(s):

Arthur Burgess

Keyword(s):

Image Quality ◽

Human Performance ◽

Ideal Observer ◽

The Ideal ◽

Decision Tasks

Download Full-text

Bayesian natural selection and the evolution of perceptual systems

Philosophical Transactions of the Royal Society B Biological Sciences ◽

10.1098/rstb.2001.1055 ◽

2002 ◽

Vol 357 (1420) ◽

pp. 419-448 ◽

Cited By ~ 50

Author(s):

Wilson S. Geisler ◽

Randy L. Diehl

Keyword(s):

Natural Selection ◽

Decision Theory ◽

Ideal Observer ◽

Statistical Decision Theory ◽

Statistical Decision ◽

Natural Stimuli ◽

Ideal Observers ◽

Formal Framework ◽

Bayesian Statistical Decision Theory ◽

Perceptual Systems

In recent years, there has been much interest in characterizing statistical properties of natural stimuli in order to better understand the design of perceptual systems. A fruitful approach has been to compare the processing of natural stimuli in real perceptual systems with that of ideal observers derived within the framework of Bayesian statistical decision theory. While this form of optimization theory has provided a deeper understanding of the information contained in natural stimuli as well as of the computational principles employed in perceptual systems, it does not directly consider the process of natural selection, which is ultimately responsible for design. Here we propose a formal framework for analysing how the statistics of natural stimuli and the process of natural selection interact to determine the design of perceptual systems. The framework consists of two complementary components. The first is a maximum fitness ideal observer, a standard Bayesian ideal observer with a utility function appropriate for natural selection. The second component is a formal version of natural selection based upon Bayesian statistical decision theory. Maximum fitness ideal observers and Bayesian natural selection are demonstrated in several examples. We suggest that the Bayesian approach is appropriate not only for the study of perceptual systems but also for the study of many other systems in biology.

Download Full-text

Human visual motion perception shows hallmarks of Bayesian structural inference

Scientific Reports ◽

10.1038/s41598-021-82175-7 ◽

2021 ◽

Vol 11 (1) ◽

Author(s):

Sichao Yang ◽

Johannes Bill ◽

Jan Drugowitsch ◽

Samuel J. Gershman

Keyword(s):

Motion Perception ◽

Visual Motion ◽

Probabilistic Reasoning ◽

Choice Model ◽

Human Motion ◽

Object Motion ◽

Ideal Observer ◽

Structure Identification ◽

Structural Inference ◽

Visual Motion Perception

AbstractMotion relations in visual scenes carry an abundance of behaviorally relevant information, but little is known about how humans identify the structure underlying a scene’s motion in the first place. We studied the computations governing human motion structure identification in two psychophysics experiments and found that perception of motion relations showed hallmarks of Bayesian structural inference. At the heart of our research lies a tractable task design that enabled us to reveal the signatures of probabilistic reasoning about latent structure. We found that a choice model based on the task’s Bayesian ideal observer accurately matched many facets of human structural inference, including task performance, perceptual error patterns, single-trial responses, participant-specific differences, and subjective decision confidence—especially, when motion scenes were ambiguous and when object motion was hierarchically nested within other moving reference frames. Our work can guide future neuroscience experiments to reveal the neural mechanisms underlying higher-level visual motion perception.

Download Full-text