Improving Inference for Neural Image Compression
- URL: http://arxiv.org/abs/2006.04240v4
- Date: Fri, 8 Jan 2021 08:50:54 GMT
- Title: Improving Inference for Neural Image Compression
- Authors: Yibo Yang, Robert Bamler, Stephan Mandt
- Abstract summary: State-of-the-art methods build on hierarchical variational autoencoders to predict a compressible latent representation of each data point.
We identify three approximation gaps which limit performance in the conventional approach.
We propose remedies for each of these three limitations based on ideas related to iterative inference.
- Score: 31.999462074510305
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: We consider the problem of lossy image compression with deep latent variable
models. State-of-the-art methods build on hierarchical variational autoencoders
(VAEs) and learn inference networks to predict a compressible latent
representation of each data point. Drawing on the variational inference
perspective on compression, we identify three approximation gaps which limit
performance in the conventional approach: an amortization gap, a discretization
gap, and a marginalization gap. We propose remedies for each of these three
limitations based on ideas related to iterative inference, stochastic annealing
for discrete optimization, and bits-back coding, resulting in the first
application of bits-back coding to lossy compression. In our experiments, which
include extensive baseline comparisons and ablation studies, we achieve new
state-of-the-art performance on lossy image compression using an established
VAE architecture, by changing only the inference method.
Related papers
- A Rate-Distortion-Classification Approach for Lossy Image Compression [0.0]
In lossy image compression, the objective is to achieve minimal signal distortion while compressing images to a specified bit rate.
To bridge the gap between image compression and visual analysis, we propose a Rate-Distortion-Classification (RDC) model for lossy image compression.
arXiv Detail & Related papers (2024-05-06T14:11:36Z) - Semantic Ensemble Loss and Latent Refinement for High-Fidelity Neural Image Compression [58.618625678054826]
This study presents an enhanced neural compression method designed for optimal visual fidelity.
We have trained our model with a sophisticated semantic ensemble loss, integrating Charbonnier loss, perceptual loss, style loss, and a non-binary adversarial loss.
Our empirical findings demonstrate that this approach significantly improves the statistical fidelity of neural image compression.
arXiv Detail & Related papers (2024-01-25T08:11:27Z) - Transferable Learned Image Compression-Resistant Adversarial Perturbations [66.46470251521947]
Adversarial attacks can readily disrupt the image classification system, revealing the vulnerability of DNN-based recognition tasks.
We introduce a new pipeline that targets image classification models that utilize learned image compressors as pre-processing modules.
arXiv Detail & Related papers (2024-01-06T03:03:28Z) - JND-Based Perceptual Optimization For Learned Image Compression [42.822121565430926]
We propose a JND-based perceptual quality loss for learned image compression schemes.
We show that the proposed method has led to better perceptual quality than the baseline model under the same bit rate.
arXiv Detail & Related papers (2023-02-25T14:49:09Z) - Estimating the Resize Parameter in End-to-end Learned Image Compression [50.20567320015102]
We describe a search-free resizing framework that can further improve the rate-distortion tradeoff of recent learned image compression models.
Our results show that our new resizing parameter estimation framework can provide Bjontegaard-Delta rate (BD-rate) improvement of about 10% against leading perceptual quality engines.
arXiv Detail & Related papers (2022-04-26T01:35:02Z) - Post-Training Quantization for Cross-Platform Learned Image Compression [15.67527732099067]
It has been witnessed that learned image compression has outperformed conventional image coding techniques.
One of the most critical issues that need to be considered is the non-deterministic calculation.
We propose to solve this problem by introducing well-developed post-training quantization.
arXiv Detail & Related papers (2022-02-15T15:41:12Z) - Reducing Redundancy in the Bottleneck Representation of the Autoencoders [98.78384185493624]
Autoencoders are a type of unsupervised neural networks, which can be used to solve various tasks.
We propose a scheme to explicitly penalize feature redundancies in the bottleneck representation.
We tested our approach across different tasks: dimensionality reduction using three different dataset, image compression using the MNIST dataset, and image denoising using fashion MNIST.
arXiv Detail & Related papers (2022-02-09T18:48:02Z) - Implicit Neural Representations for Image Compression [103.78615661013623]
Implicit Neural Representations (INRs) have gained attention as a novel and effective representation for various data types.
We propose the first comprehensive compression pipeline based on INRs including quantization, quantization-aware retraining and entropy coding.
We find that our approach to source compression with INRs vastly outperforms similar prior work.
arXiv Detail & Related papers (2021-12-08T13:02:53Z) - High-Fidelity Generative Image Compression [39.04379573099481]
We study how to combine Gene Adrial Networks and learned compression to obtain a state-of-the-art generative lossy compression system.
In particular, we investigate normalization layers, generator and discriminator architectures, training strategies, as well as perceptual losses.
arXiv Detail & Related papers (2020-06-17T16:21:10Z) - Learning End-to-End Lossy Image Compression: A Benchmark [90.35363142246806]
We first conduct a comprehensive literature survey of learned image compression methods.
We describe milestones in cutting-edge learned image-compression methods, review a broad range of existing works, and provide insights into their historical development routes.
By introducing a coarse-to-fine hyperprior model for entropy estimation and signal reconstruction, we achieve improved rate-distortion performance.
arXiv Detail & Related papers (2020-02-10T13:13:43Z)
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.