On the relation between statistical learning and perceptual distances
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 relationships 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 training data, as well as how these induced distances are correlated with human perception. Finally, we find perceptual distances do not always lead to noticeable gains in performance over Euclidean distance in common image processing tasks, except when data is scarce and the perceptual distance provides regularization. We propose this may be due to a \emph{double-counting} effect of the image statistics, once in the perceptual distance and once in the training procedure.
Code (0)
등록된 구현이 없습니다.
Tasks
BIG-bench Machine LearningPerceptual DistanceRelationSimilar Papers 제목 키워드 기반
Do better ImageNet classifiers assess perceptual similarity better?
Perceptual distances between images, as measured in the space of pre-trained deep features, have outperformed prior low-level, pixel-based metrics on assessing perceptual similarity. While the capabilities of older and l…
Controlling Wasserstein Distances by Kernel Norms with Application to Compressive Statistical Learning
Comparing probability distributions is at the crux of many machine learning algorithms. Maximum Mean Discrepancies (MMD) and Wasserstein distances are two classes of distances between probability distributions that have …
DPLM: A Deep Perceptual Spatial-Audio Localization Metric
Subjective evaluations are critical for assessing the perceptual realism of sounds in audio-synthesis driven technologies like augmented and virtual reality. However, they are challenging to set up, fatiguing for users, …
Audio SynthesisHuman Echolocation in Static Situations: Auditory Models of Detection Thresholds for Distance, Pitch, Loudness and Timbre
We investigated, by using auditory models, how three perceptual parameters, loudness, pitch and sharpness, determine human echolocation. We used acoustic recordings from two previous studies, both from stationary situati…
Generating Images with Perceptual Similarity Metrics based on Deep Networks
Image-generating machine learning models are typically trained with loss functions based on distance in the image space. This often leads to over-smoothed results. We propose a class of loss functions, which we call deep…
Image Generation