# Parametric PerceptNet: A bio-inspired deep-net trained for Image Quality Assessment

arXiv: https://arxiv.org/abs/2412.03210 · HTML: https://mlsanity.com/paper/2412.03210/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 28 of its 148 references that are in the map.
- First posted on arXiv 4 Dec 2024.

## Builds on (most cited first, 28 of 28)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness](https://mlsanity.com/paper/1811.12231/) (2018)
- [Density Modeling of Images using a Generalized Normalization Transformation](https://mlsanity.com/paper/1511.06281/) (2015)
- [Beyond accuracy: quantifying trial-by-trial behaviour of CNNs and humans by measuring error consistency](https://mlsanity.com/paper/2006.16736/) (2020)
- [On scientific understanding with artificial intelligence](https://mlsanity.com/paper/2204.01467/) (2022)
- [Gabor Convolutional Networks](https://mlsanity.com/paper/1705.01450/) (2017)
- [Neither hype nor gloom do DNNs justice](https://mlsanity.com/paper/2312.05355/) (2023)
- [Do better ImageNet classifiers assess perceptual similarity better?](https://mlsanity.com/paper/2203.04946/) (2022)
- [GaborNet: Gabor filters with learnable parameters in deep convolutional neural networks](https://mlsanity.com/paper/1904.13204/) (2019)
- [Perceptually Optimized Image Rendering](https://mlsanity.com/paper/1701.06641/) (2017)
- [On-Off Center-Surround Receptive Fields for Accurate and Robust Image Classification](https://mlsanity.com/paper/2106.07091/) (2021)
- [Contrast Sensitivity Functions in Autoencoders](https://mlsanity.com/paper/2103.00481/) (2021)
- [Normalizing the Normalizers: Comparing and Extending Network Normalization Schemes](https://mlsanity.com/paper/1611.04520/) (2016)
- [PerceptNet: A Human Visual System Inspired Neural Network for Estimating Perceptual Distance](https://mlsanity.com/paper/1910.12548/) (2019)
- [Nonlinearities and Adaptation of Color Vision from Sequential Principal Curves Analysis](https://mlsanity.com/paper/1602.00236/) (2016)
- [Derivatives and Inverse of Cascaded Linear+Nonlinear Neural Models](https://mlsanity.com/paper/1711.00526/) (2017)
- [MindSet: Vision. A toolbox for testing DNNs on key psychological experiments](https://mlsanity.com/paper/2404.05290/) (2024)
- [Spatio-Chromatic Information available from different Neural Layers via Gaussianization](https://mlsanity.com/paper/1910.01559/) (2019)
- [Visual Information flow in Wilson-Cowan networks](https://mlsanity.com/paper/1907.13046/) (2019)
- [Integrating Flexible Normalization into Mid-Level Representations of Deep Convolutional Neural Networks](https://mlsanity.com/paper/1806.01823/) (2018)
- [Cortical Divisive Normalization from Wilson-Cowan Neural Dynamics](https://mlsanity.com/paper/1906.08246/) (2019)
- [GMConv: Modulating Effective Receptive Fields for Convolutional Kernels](https://mlsanity.com/paper/2302.04544/) (2023)
- [Assessing invariance to affine transformations in image quality metrics](https://mlsanity.com/paper/2407.17927/) (2024)
- [On the Suitable Domain for SVM Training in Image Coding](https://mlsanity.com/paper/1310.5082/) (2013)
- [Estimating the contribution of early and late noise in vision from psychophysical data](https://mlsanity.com/paper/2012.06608/) (2020)
- [Image Segmentation via Divisive Normalization: dealing with environmental diversity](https://mlsanity.com/paper/2407.17829/) (2024)

## Abstract (arXiv)

Human vision models are at the core of image processing. For instance, classical approaches to the problem of image quality are based on models that include knowledge about human vision. However, nowadays, deep learning approaches have obtained competitive results by simply approaching this problem as regression of human decisions, and training an standard network on human-rated datasets. These approaches have the advantages of being easily adaptable to a particular problem and they fit very efficiently when data is available. However, mainly due to the excess of parameters, they have the problems of lack of interpretability, and over-fitting. Here we propose a vision model that combines the best of both worlds by using a parametric neural network architecture. We parameterize the layers to have bioplausible functionality, and provide a set of bioplausible parameters. We analyzed different versions of the model and compared it with the non-parametric version. The parametric models achieve a three orders of magnitude reduction in the number of parameters without suffering in regression performance. Furthermore, we show that the parametric models behave better during training and are easier to interpret as vision models. Interestingly, we find that, even initialized with bioplausible trained for regression using human rated datasets, which we call the feature-spreading problem. This suggests that the deep learning approach is inherently flawed, and emphasizes the need to evaluate and train models beyond regression.