Analyzing and Mitigating JPEG Compression Defects in Deep Learning

• URL: http://arxiv.org/abs/2011.08932v2
• Date: Mon, 20 Sep 2021 12:28:30 GMT
• Title: Analyzing and Mitigating JPEG Compression Defects in Deep Learning
• Authors: Max Ehrlich, Larry Davis, Ser-Nam Lim, Abhinav Shrivastava
• Abstract summary: We present a unified study of the effects of JPEG compression on a range of common tasks and datasets. We show that there is a significant penalty on common performance metrics for high compression.
• Score: 69.04777875711646
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: With the proliferation of deep learning methods, many computer vision problems which were considered academic are now viable in the consumer setting. One drawback of consumer applications is lossy compression, which is necessary from an engineering standpoint to efficiently and cheaply store and transmit user images. Despite this, there has been little study of the effect of compression on deep neural networks and benchmark datasets are often losslessly compressed or compressed at high quality. Here we present a unified study of the effects of JPEG compression on a range of common tasks and datasets. We show that there is a significant penalty on common performance metrics for high compression. We test several methods for mitigating this penalty, including a novel method based on artifact correction which requires no labels to train.

Related papers

• 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)
• Deep learning based Image Compression for Microscopy Images: An Empirical Study [3.915183869199319]
  This study analyzes classic and deep learning based image compression methods, and their impact on deep learning based image processing models. To compress images in such a wanted way, multiple classical lossy image compression techniques are compared to several AI-based compression models. We found that AI-based compression techniques largely outperform the classic ones and will minimally affect the downstream label-free task in 2D cases.
  arXiv  Detail & Related papers  (2023-11-02T16:00:32Z)
• HFLIC: Human Friendly Perceptual Learned Image Compression with Reinforced Transform [16.173583505483272]
  Current learning-based image compression methods often sacrifice human-friendly compression and require long decoding times. We propose enhancements to the backbone network and loss function of existing image compression model, focusing on improving human perception and efficiency.
  arXiv  Detail & Related papers  (2023-05-12T14:35:27Z)
• Convolutional Neural Network (CNN) to reduce construction loss in JPEG compression caused by Discrete Fourier Transform (DFT) [0.0]
  Convolutional Neural Networks (CNN) have received more attention than most other types of deep neural networks. In this work, an effective image compression method is purposed using autoencoders.
  arXiv  Detail & Related papers  (2022-08-26T12:46:16Z)
• Crowd Counting on Heavily Compressed Images with Curriculum Pre-Training [90.76576712433595]
  Applying lossy compression on images processed by deep neural networks can lead to significant accuracy degradation. Inspired by the curriculum learning paradigm, we present a novel training approach called curriculum pre-training (CPT) for crowd counting on compressed images.
  arXiv  Detail & Related papers  (2022-08-15T08:43:21Z)
• 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)
• Learned Image Compression for Machine Perception [17.40776913809306]
  We develop a framework that produces a compression format suitable for both human perception and machine perception. We show that representations can be learned that simultaneously optimize for compression and performance on core vision tasks.
  arXiv  Detail & Related papers  (2021-11-03T14:39:09Z)
• Towards Robust Data Hiding Against (JPEG) Compression: A Pseudo-Differentiable Deep Learning Approach [78.05383266222285]
  It is still an open challenge to achieve the goal of data hiding that can be against these compressions. Deep learning has shown large success in data hiding, while non-differentiability of JPEG makes it challenging to train a deep pipeline for improving robustness against lossy compression. In this work, we propose a simple yet effective approach to address all the above limitations at once.
  arXiv  Detail & Related papers  (2020-12-30T12:30:09Z)
• Quantization Guided JPEG Artifact Correction [69.04777875711646]
  We develop a novel architecture for artifact correction using the JPEG files quantization matrix. This allows our single model to achieve state-of-the-art performance over models trained for specific quality settings.
  arXiv  Detail & Related papers  (2020-04-17T00:10:08Z)

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.