Optimally Controllable Perceptual Lossy Compression

• URL: http://arxiv.org/abs/2206.10082v1
• Date: Tue, 21 Jun 2022 02:48:35 GMT
• Title: Optimally Controllable Perceptual Lossy Compression
• Authors: Zeyu Yan, Fei Wen, Peilin Liu
• Abstract summary: Recent studies in lossy compression show that distortion and perceptual quality are at odds with each other. To attain different perceptual quality, different decoders have to be trained. We present a nontrivial finding that only two decoders are sufficient for optimally achieving arbitrary D-P tradeoffs.
• Score: 16.208548355509127
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent studies in lossy compression show that distortion and perceptual quality are at odds with each other, which put forward the tradeoff between distortion and perception (D-P). Intuitively, to attain different perceptual quality, different decoders have to be trained. In this paper, we present a nontrivial finding that only two decoders are sufficient for optimally achieving arbitrary (an infinite number of different) D-P tradeoff. We prove that arbitrary points of the D-P tradeoff bound can be achieved by a simple linear interpolation between the outputs of a minimum MSE decoder and a specifically constructed perfect perceptual decoder. Meanwhile, the perceptual quality (in terms of the squared Wasserstein-2 distance metric) can be quantitatively controlled by the interpolation factor. Furthermore, to construct a perfect perceptual decoder, we propose two theoretically optimal training frameworks. The new frameworks are different from the distortion-plus-adversarial loss based heuristic framework widely used in existing methods, which are not only theoretically optimal but also can yield state-of-the-art performance in practical perceptual decoding. Finally, we validate our theoretical finding and demonstrate the superiority of our frameworks via experiments. Code is available at: https://github.com/ZeyuYan/Controllable-Perceptual-Compression

Related papers

• A Theoretical Perspective for Speculative Decoding Algorithm [60.79447486066416]
  One effective way to accelerate inference is emphSpeculative Decoding, which employs a small model to sample a sequence of draft tokens and a large model to validate. This paper tackles this gap by conceptualizing the decoding problem via markov chain abstraction and studying the key properties, emphoutput quality and inference acceleration, from a theoretical perspective.
  arXiv  Detail & Related papers  (2024-10-30T01:53:04Z)
• Practical Conformer: Optimizing size, speed and flops of Conformer for on-Device and cloud ASR [67.63332492134332]
  We design an optimized conformer that is small enough to meet on-device restrictions and has fast inference on TPUs. Our proposed encoder can double as a strong standalone encoder in on device, and as the first part of a high-performance ASR pipeline.
  arXiv  Detail & Related papers  (2023-03-31T23:30:48Z)
• Flexible Neural Image Compression via Code Editing [8.499248314440557]
  Neural image compression (NIC) has outperformed traditional image codecs in ratedistortion (R-D) performance. It usually requires a dedicated encoder-decoder pair for each point on R-D curve, which greatly hinders its practical deployment. We propose Code Editing, a highly flexible coding method for NIC based on semi-amortized inference and adaptive quantization.
  arXiv  Detail & Related papers  (2022-09-19T09:41:43Z)
• String-based Molecule Generation via Multi-decoder VAE [56.465033997245776]
  We investigate the problem of string-based molecular generation via variational autoencoders (VAEs) We propose a simple, yet effective idea to improve the performance of VAE for the task. In our experiments, the proposed VAE model particularly performs well for generating a sample from out-of-domain distribution.
  arXiv  Detail & Related papers  (2022-08-23T03:56:30Z)
• Improved decoding of circuit noise and fragile boundaries of tailored surface codes [61.411482146110984]
  We introduce decoders that are both fast and accurate, and can be used with a wide class of quantum error correction codes. Our decoders, named belief-matching and belief-find, exploit all noise information and thereby unlock higher accuracy demonstrations of QEC. We find that the decoders led to a much higher threshold and lower qubit overhead in the tailored surface code with respect to the standard, square surface code.
  arXiv  Detail & Related papers  (2022-03-09T18:48:54Z)
• 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)
• Universal Rate-Distortion-Perception Representations for Lossy Compression [31.28856752892628]
  We consider the notion of universal representations in which one may fix an encoder and vary the decoder to achieve any point within a collection of distortion and perception constraints. We prove that the corresponding information-theoretic universal rate-distortion-perception is operationally achievable in an approximate sense.
  arXiv  Detail & Related papers  (2021-06-18T18:52:08Z)
• On Perceptual Lossy Compression: The Cost of Perceptual Reconstruction and An Optimal Training Framework [12.13586501618741]
  We show that the cost of achieving perfect perception quality is exactly a doubling of the lowest achievable MSE distortion. We propose a novel training framework to achieve the lowest MSE distortion under perfect perception constraint at a given bit rate.
  arXiv  Detail & Related papers  (2021-06-05T02:53:38Z)
• Dissecting Supervised Constrastive Learning [24.984074794337157]
  Minimizing cross-entropy over the softmax scores of a linear map composed with a high-capacity encoder is arguably the most popular choice for training neural networks on supervised learning tasks. We show that one can directly optimize the encoder instead, to obtain equally (or even more) discriminative representations via a supervised variant of a contrastive objective.
  arXiv  Detail & Related papers  (2021-02-17T15:22:38Z)
• Learning to Learn to Compress [25.23586503813838]
  We present an end-to-end meta-learned system for image compression. We propose a new training paradigm for learned image compression based on meta-learning.
  arXiv  Detail & Related papers  (2020-07-31T13:13:53Z)
• Suppress and Balance: A Simple Gated Network for Salient Object Detection [89.88222217065858]
  We propose a simple gated network (GateNet) to solve both issues at once. With the help of multilevel gate units, the valuable context information from the encoder can be optimally transmitted to the decoder. In addition, we adopt the atrous spatial pyramid pooling based on the proposed "Fold" operation (Fold-ASPP) to accurately localize salient objects of various scales.
  arXiv  Detail & Related papers  (2020-07-16T02:00:53Z)

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.