On Self-Adaptive Perception Loss Function for Sequential Lossy Compression

• URL: http://arxiv.org/abs/2502.10628v1
• Date: Sat, 15 Feb 2025 01:41:53 GMT
• Title: On Self-Adaptive Perception Loss Function for Sequential Lossy Compression
• Authors: Sadaf Salehkalaibar, Buu Phan, Likun Cai, Joao Atz Dick, Wei Yu, Jun Chen, Ashish Khisti,
• Abstract summary: We consider causal, low-latency, sequential lossy compression, with mean squared-error (MSE) as the distortion loss, and a perception loss function (PLF) to enhance the realism of reconstructions. We establish the theoretical rate-distortion-perception function for first-order Markov sources and analyze the Gaussian model in detail. The proposed metric is referred to as self-adaptive perception loss function (PLF-SA), as its behavior adapts to the quality of reconstructed frames.
• Score: 29.361832071511795
• License:
• Abstract: We consider causal, low-latency, sequential lossy compression, with mean squared-error (MSE) as the distortion loss, and a perception loss function (PLF) to enhance the realism of reconstructions. As the main contribution, we propose and analyze a new PLF that considers the joint distribution between the current source frame and the previous reconstructions. We establish the theoretical rate-distortion-perception function for first-order Markov sources and analyze the Gaussian model in detail. From a qualitative perspective, the proposed metric can simultaneously avoid the error-permanence phenomenon and also better exploit the temporal correlation between high-quality reconstructions. The proposed metric is referred to as self-adaptive perception loss function (PLF-SA), as its behavior adapts to the quality of reconstructed frames. We provide a detailed comparison of the proposed perception loss function with previous approaches through both information theoretic analysis as well as experiments involving moving MNIST and UVG datasets.

Related papers

• Perceptual-Distortion Balanced Image Super-Resolution is a Multi-Objective Optimization Problem [23.833099288826045]
  Training Single-Image Super-Resolution (SISR) models using pixel-based regression losses can achieve high distortion metrics scores. However, they often results in blurry images due to insufficient recovery of high-frequency details. We propose a novel method that incorporates Multi-Objective Optimization (MOO) into the training process of SISR models to balance perceptual quality and distortion.
  arXiv  Detail & Related papers  (2024-09-05T02:14:04Z)
• Low-resolution Prior Equilibrium Network for CT Reconstruction [3.5639148953570836]
  We present a novel deep learning-based CT reconstruction model, where the low-resolution image is introduced to obtain an effective regularization term for improving the networks robustness. Experimental results on both sparse-view and limited-angle reconstruction problems are provided, demonstrating that our end-to-end low-resolution prior equilibrium model outperforms other state-of-the-art methods in terms of noise reduction, contrast-to-noise ratio, and preservation of edge details.
  arXiv  Detail & Related papers  (2024-01-28T13:59:58Z)
• On the Dynamics Under the Unhinged Loss and Beyond [104.49565602940699]
  We introduce the unhinged loss, a concise loss function, that offers more mathematical opportunities to analyze closed-form dynamics. The unhinged loss allows for considering more practical techniques, such as time-vary learning rates and feature normalization.
  arXiv  Detail & Related papers  (2023-12-13T02:11:07Z)
• A PAC-Bayesian Perspective on the Interpolating Information Criterion [54.548058449535155]
  We show how a PAC-Bayes bound is obtained for a general class of models, characterizing factors which influence performance in the interpolating regime. We quantify how the test error for overparameterized models achieving effectively zero training error depends on the quality of the implicit regularization imposed by e.g. the combination of model, parameter-initialization scheme.
  arXiv  Detail & Related papers  (2023-11-13T01:48:08Z)
• On the Choice of Perception Loss Function for Learned Video Compression [31.865079406929276]
  We study causal, low-latency, sequential video compression when the output is subjected to a mean squared-error (MSE) distortion loss and a perception loss to target realism. We show that the choice of perception loss functions (PLFs) can have a significant effect on the reconstruction, especially at low-bit rates.
  arXiv  Detail & Related papers  (2023-05-30T14:24:40Z)
• Compressed Regression over Adaptive Networks [58.79251288443156]
  We derive the performance achievable by a network of distributed agents that solve, adaptively and in the presence of communication constraints, a regression problem. We devise an optimized allocation strategy where the parameters necessary for the optimization can be learned online by the agents.
  arXiv  Detail & Related papers  (2023-04-07T13:41:08Z)
• DiracDiffusion: Denoising and Incremental Reconstruction with Assured Data-Consistency [24.5360032541275]
  Diffusion models have established new state of the art in a multitude of computer vision tasks, including image restoration. We propose a novel framework for inverse problem solving, namely we assume that the observation comes from a degradation process that gradually degrades and noises the original clean image. Our technique maintains consistency with the original measurement throughout the reverse process, and allows for great flexibility in trading off perceptual quality for improved distortion metrics and sampling speedup via early-stopping.
  arXiv  Detail & Related papers  (2023-03-25T04:37:20Z)
• Making Reconstruction-based Method Great Again for Video Anomaly Detection [64.19326819088563]
  Anomaly detection in videos is a significant yet challenging problem. Existing reconstruction-based methods rely on old-fashioned convolutional autoencoders. We propose a new autoencoder model for enhanced consecutive frame reconstruction.
  arXiv  Detail & Related papers  (2023-01-28T01:57:57Z)
• Relationship Quantification of Image Degradations [72.98190570967937]
  Degradation Relationship Index (DRI) is defined as the mean drop rate difference in the validation loss between two models. DRI always predicts performance improvement by using the specific degradation as an auxiliary to train models. We propose a simple but effective method to estimate whether the given degradation combinations could improve the performance on the anchor degradation.
  arXiv  Detail & Related papers  (2022-12-08T09:05:19Z)
• Variational Laplace Autoencoders [53.08170674326728]
  Variational autoencoders employ an amortized inference model to approximate the posterior of latent variables. We present a novel approach that addresses the limited posterior expressiveness of fully-factorized Gaussian assumption. We also present a general framework named Variational Laplace Autoencoders (VLAEs) for training deep generative models.
  arXiv  Detail & Related papers  (2022-11-30T18:59:27Z)
• Learned convex regularizers for inverse problems [3.294199808987679]
  We propose to learn a data-adaptive input- neural network (ICNN) as a regularizer for inverse problems. We prove the existence of a sub-gradient-based algorithm that leads to a monotonically decreasing error in the parameter space with iterations. We show that the proposed convex regularizer is at least competitive with and sometimes superior to state-of-the-art data-driven techniques for inverse problems.
  arXiv  Detail & Related papers  (2020-08-06T18:58:35Z)

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.