Learned Image Compression for Machine Perception
- URL: http://arxiv.org/abs/2111.02249v1
- Date: Wed, 3 Nov 2021 14:39:09 GMT
- Title: Learned Image Compression for Machine Perception
- Authors: Felipe Codevilla, Jean Gabriel Simard, Ross Goroshin and Chris Pal
- Abstract summary: 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.
- Score: 17.40776913809306
- License: http://creativecommons.org/licenses/by-nc-sa/4.0/
- Abstract: Recent work has shown that learned image compression strategies can
outperform standard hand-crafted compression algorithms that have been
developed over decades of intensive research on the rate-distortion trade-off.
With growing applications of computer vision, high quality image reconstruction
from a compressible representation is often a secondary objective. Compression
that ensures high accuracy on computer vision tasks such as image segmentation,
classification, and detection therefore has the potential for significant
impact across a wide variety of settings. In this work, 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.
Our approach allows models to be trained directly from compressed
representations, and this approach yields increased performance on new tasks
and in low-shot learning settings. We present results that improve upon
segmentation and detection performance compared to standard high quality JPGs,
but with representations that are four to ten times smaller in terms of bits
per pixel. Further, unlike naive compression methods, at a level ten times
smaller than standard JEPGs, segmentation and detection models trained from our
format suffer only minor degradation in performance.
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) - 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) - Machine Perception-Driven Image Compression: A Layered Generative
Approach [32.23554195427311]
layered generative image compression model is proposed to achieve high human vision-oriented image reconstructed quality.
Task-agnostic learning-based compression model is proposed, which effectively supports various compressed domain-based analytical tasks.
Joint optimization schedule is adopted to acquire best balance point among compression ratio, reconstructed image quality, and downstream perception performance.
arXiv Detail & Related papers (2023-04-14T02:12:38Z) - 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) - Learning-based Compression for Material and Texture Recognition [23.668803886355683]
This paper is concerned with learning-based compression schemes whose compressed-domain representations can be utilized to perform visual processing and computer vision tasks directly in the compressed domain.
We adopt the learning-based JPEG-AI framework for performing material and texture recognition using the compressed-domain latent representation at varing bit-rates.
It is also shown that the compressed-domain classification can yield a competitive performance in terms of Top-1 and Top-5 accuracy while using a smaller reduced-complexity classification model.
arXiv Detail & Related papers (2021-04-16T23:16:26Z) - Analyzing and Mitigating JPEG Compression Defects in Deep Learning [69.04777875711646]
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.
arXiv Detail & Related papers (2020-11-17T20:32:57Z) - 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) - Discernible Image Compression [124.08063151879173]
This paper aims to produce compressed images by pursuing both appearance and perceptual consistency.
Based on the encoder-decoder framework, we propose using a pre-trained CNN to extract features of the original and compressed images.
Experiments on benchmarks demonstrate that images compressed by using the proposed method can also be well recognized by subsequent visual recognition and detection models.
arXiv Detail & Related papers (2020-02-17T07:35:08Z) - Saliency Driven Perceptual Image Compression [6.201592931432016]
The paper demonstrates that the popularly used evaluations metrics such as MS-SSIM and PSNR are inadequate for judging the performance of image compression techniques.
A new metric is proposed, which is learned on perceptual similarity data specific to image compression.
The model not only generates images which are visually better but also gives superior performance for subsequent computer vision tasks.
arXiv Detail & Related papers (2020-02-12T13:43:17Z)
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.