mlsanityData to 7 Oct 2026

TACTIC: Joint Rate-Distortion-Accuracy Optimisation for Low Bitrate Compression

arXiv 2109.10658 ↗First posted 22 Sep 2021cs.CV cs.IT eess.IVcited by 0

Not on the map. Why?

Abstract (arXiv)

We present TACTIC: Task-Aware Compression Through Intelligent Coding. Our lossy compression model learns based on the rate-distortion-accuracy trade-off for a specific task. By considering what information is important for the follow-on problem, the system trades off visual fidelity for good task performance at a low bitrate. When compared against JPEG at the same bitrate, our approach is able to improve the accuracy of ImageNet subset classification by 4.5%. We also demonstrate the applicability of our approach to other problems, providing a 3.4% accuracy and 4.9% mean IoU improvements in performance over task-agnostic compression for semantic segmentation.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 20 of its 24 references that are in the map. First posted on arXiv 22 Sep 2021.

Builds on

20 of 24 references.

References · 20

  1. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  2. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  3. 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
  4. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
  5. 2018Variational image compression with a scale hyperpriorcited by 910
  6. 2020High-Fidelity Generative Image Compressioncited by 331
  7. 2018Generative Adversarial Networks for Extreme Learned Image Compressioncited by 213
  8. 2017Real-Time Adaptive Image Compressioncited by 127
  9. 2018Deep Generative Models for Distribution-Preserving Lossy Compressioncited by 59
  10. 2020Quantization Guided JPEG Artifact Correctioncited by 57
  11. 2018Towards Image Understanding from Deep Compression without Decodingcited by 52
  12. 2020Fidelity-Controllable Extreme Image Compression with Generative Adversarial Networkscited by 28
8 more
  1. 2018DeepN-JPEG: A Deep Neural Network Favorable JPEG-based Image Compression Frameworkcited by 23
  2. 2020The Rate-Distortion-Accuracy Tradeoff: JPEG Case Studycited by 22
  3. 2020Training CNNs in Presence of JPEG Compression: Multimedia Forensics vs Computer Visioncited by 17
  4. 2020A GAN-based Tunable Image Compression Systemcited by 14
  5. 2020On the Impact of Lossy Image and Video Compression on the Performance of Deep Convolutional Neural Network Architecturescited by 11
  6. 2020Learning a Single Model with a Wide Range of Quality Factors for JPEG Image Artifacts Removalcited by 11
  7. 2020Optimizing JPEG Quantization for Classification Networkscited by 6
  8. 2020Adapting JPEG XS gains and priorities to tasks and contentscited by 5

Built on by

Not cited yet.