paper-with-me

홈 › Papers

Analysis and Interpretation of Deep CNN Representations as Perceptual Quality Features

2019-09-25 · Taimoor Tariq, Munchurl Kim

Pre-trained Deep Convolutional Neural Network (CNN) features have popularly been used as full-reference perceptual quality features for CNN based image quality assessment, super-resolution, image restoration and a variety of image-to-image translation problems. In this paper, to get more insight, we link basic human visual perception to characteristics of learned deep CNN representations as a novel and first attempt to interpret them. We characterize the frequency and orientation tuning of channels in trained object detection deep CNNs (e.g., VGG-16) by applying grating stimuli of different spatial frequencies and orientations as input. We observe that the behavior of CNN channels as spatial frequency and orientation selective filters can be used to link basic human visual perception models to their characteristics. Doing so, we develop a theory to get more insight into deep CNN representations as perceptual quality features. We conclude that sensitivity to spatial frequencies that have lower contrast masking thresholds in human visual perception and a definite and strong orientation selectivity are important attributes of deep CNN channels that deliver better perceptual quality features.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Image Quality AssessmentImage RestorationImage-to-Image Translationobject-detectionObject DetectionSuper-Resolution

Similar Papers 제목 키워드 기반

Why Are Deep Representations Good Perceptual Quality Features?

2018-12-02 · ECCV 2020 8 · Taimoor Tariq, Okan Tarhan Tursun, Munchurl Kim, Piotr Didyk

Recently, intermediate feature maps of pre-trained convolutional neural networks have shown significant perceptual quality improvements, when they are used in the loss function for training new networks. It is believed t…

Image Quality AssessmentImage ReconstructionImage RestorationImage Super-Resolution+4

Learnt Deep Hyperparameter selection in Adversarial Training for compressed video enhancement with perceptual critic

2023-02-28 · Darren Ramsook, Anil Kokaram

Image based Deep Feature Quality Metrics (DFQMs) have been shown to better correlate with subjective perceptual scores over traditional metrics. The fundamental focus of these DFQMs is to exploit internal representations…

feature selectionVideo Enhancement

Perceptual misalignment of texture representations in convolutional neural networks

2026-04-01 · Ludovica de Paolis, Fabio Anselmi, Alessio Ansuini, Eugenio Piasini arxiv

Mathematical modeling of visual textures traces back to Julesz's intuition that texture perception in humans is based on local correlations between image features. An influential approach for texture analysis and generat…

Object Recognition

DExter: Learning and Controlling Performance Expression with Diffusion Models

2024-06-21 · huan zhang, Shreyan Chowdhury, Carlos Eduardo Cancino-Chacón, Jinhua Liang 외

In the pursuit of developing expressive music performance models using artificial intelligence, this paper introduces DExter, a new approach leveraging diffusion probabilistic models to render Western classical piano per…

Music Performance Rendering

AgenticIQA: An Agentic Framework for Adaptive and Interpretable Image Quality Assessment

2025-09-30 · Hanwei Zhu, Yu Tian, Keyan Ding, Baoliang Chen 외 arxiv

Image quality assessment (IQA) is inherently complex, as it reflects both the quantification and interpretation of perceptual quality rooted in the human visual system. Conventional approaches typically rely on fixed mod…

Image Quality Assessment