On the relation between statistical learning and perceptual distances
- URL: http://arxiv.org/abs/2106.04427v1
- Date: Tue, 8 Jun 2021 14:56:56 GMT
- Title: On the relation between statistical learning and perceptual distances
- Authors: Alexander Hepburn and Valero Laparra and Raul Santos-Rodriguez and
Johannes Ball\'e and Jes\'us Malo
- Abstract summary: We show that perceptual sensitivity is correlated with the probability of an image in its close neighborhood.
We also explore the relation between distances induced by autoencoders and the probability distribution of the data used for training them.
- Score: 61.25815733012866
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: It has been demonstrated many times that the behavior of the human visual
system is connected to the statistics of natural images. Since machine learning
relies on the statistics of training data as well, the above connection has
interesting implications when using perceptual distances (which mimic the
behavior of the human visual system) as a loss function. In this paper, we aim
to unravel the non-trivial relationship between the probability distribution of
the data, perceptual distances, and unsupervised machine learning. To this end,
we show that perceptual sensitivity is correlated with the probability of an
image in its close neighborhood. We also explore the relation between distances
induced by autoencoders and the probability distribution of the data used for
training them, as well as how these induced distances are correlated with human
perception. Finally, we discuss why perceptual distances might not lead to
noticeable gains in performance over standard Euclidean distances in common
image processing tasks except when data is scarce and the perceptual distance
provides regularization.
Related papers
- Graph-based Complexity for Causal Effect by Empirical Plug-in [56.14597641617531]
This paper focuses on the computational complexity of computing empirical plug-in estimates for causal effect queries.
We show that computation can be done efficiently, potentially in time linear in the data size, depending on the estimand's hypergraph.
arXiv Detail & Related papers (2024-11-15T07:42:01Z) - The Effect of Perceptual Metrics on Music Representation Learning for Genre Classification [42.14708549155406]
We show that models trained with perceptual metrics as loss functions can capture perceptually meaningful features.
We demonstrate that using features extracted from autoencoders trained with perceptual losses can improve performance on music understanding tasks.
arXiv Detail & Related papers (2024-09-25T16:29:21Z) - Estimating the distribution of numerosity and non-numerical visual magnitudes in natural scenes using computer vision [0.08192907805418582]
We show that in natural visual scenes the frequency of appearance of different numerosities follows a power law distribution.
We show that the correlational structure for numerosity and continuous magnitudes is stable across datasets and scene types.
arXiv Detail & Related papers (2024-09-17T09:49:29Z) - Modeling User Preferences via Brain-Computer Interfacing [54.3727087164445]
We use Brain-Computer Interfacing technology to infer users' preferences, their attentional correlates towards visual content, and their associations with affective experience.
We link these to relevant applications, such as information retrieval, personalized steering of generative models, and crowdsourcing population estimates of affective experiences.
arXiv Detail & Related papers (2024-05-15T20:41:46Z) - A Novel Loss Function Utilizing Wasserstein Distance to Reduce
Subject-Dependent Noise for Generalizable Models in Affective Computing [0.4818210066519976]
Emotions are an essential part of human behavior that can impact thinking, decision-making, and communication skills.
The ability to accurately monitor and identify emotions can be useful in many human-centered applications such as behavioral training, tracking emotional well-being, and development of human-computer interfaces.
arXiv Detail & Related papers (2023-08-17T01:15:26Z) - A Probabilistic Transformation of Distance-Based Outliers [2.1055643409860743]
We describe a generic transformation of distance-based outlier scores into interpretable, probabilistic estimates.
The transformation is ranking-stable and increases the contrast between normal and outlier data points.
Our work generalizes to a wide range of distance-based outlier detection methods.
arXiv Detail & Related papers (2023-05-16T14:05:30Z) - DOMINO: Visual Causal Reasoning with Time-Dependent Phenomena [59.291745595756346]
We propose a set of visual analytics methods that allow humans to participate in the discovery of causal relations associated with windows of time delay.
Specifically, we leverage a well-established method, logic-based causality, to enable analysts to test the significance of potential causes.
Since an effect can be a cause of other effects, we allow users to aggregate different temporal cause-effect relations found with our method into a visual flow diagram.
arXiv Detail & Related papers (2023-03-12T03:40:21Z) - A temporally quantized distribution of pupil diameters as a new feature
for cognitive load classification [1.4469849628263638]
We present a new feature that can be used to classify cognitive load based on pupil information.
The applications of determining Cognitive Load from pupil data are numerous and could lead to pre-warning systems for burnouts.
arXiv Detail & Related papers (2023-03-03T07:52:16Z) - Dataset Bias in Human Activity Recognition [57.91018542715725]
This contribution statistically curates the training data to assess to what degree the physical characteristics of humans influence HAR performance.
We evaluate the performance of a state-of-the-art convolutional neural network on two HAR datasets that vary in the sensors, activities, and recording for time-series HAR.
arXiv Detail & Related papers (2023-01-19T12:33:50Z) - DynImp: Dynamic Imputation for Wearable Sensing Data Through Sensory and
Temporal Relatedness [78.98998551326812]
We argue that traditional methods have rarely made use of both times-series dynamics of the data as well as the relatedness of the features from different sensors.
We propose a model, termed as DynImp, to handle different time point's missingness with nearest neighbors along feature axis.
We show that the method can exploit the multi-modality features from related sensors and also learn from history time-series dynamics to reconstruct the data under extreme missingness.
arXiv Detail & Related papers (2022-09-26T21:59:14Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.