mlsanityData to 7 Oct 2026

Deep Residual Learning in the JPEG Transform Domain

arXiv 1812.11690 ↗First posted 31 Dec 2018cs.LG cs.CV stat.MLcited by 44

Not on the map. Why?

Abstract (arXiv)

We introduce a general method of performing Residual Network inference and learning in the JPEG transform domain that allows the network to consume compressed images as input. Our formulation leverages the linearity of the JPEG transform to redefine convolution and batch normalization with a tune-able numerical approximation for ReLu. The result is mathematically equivalent to the spatial domain network up to the ReLu approximation accuracy. A formulation for image classification and a model conversion algorithm for spatial domain networks are given as examples of the method. We show that the sparsity of the JPEG format allows for faster processing of images with little to no penalty in the network accuracy.

Key facts. Cited by 44 papers in the map (data through 7 Oct 2026). First posted on arXiv 31 Dec 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 9; 2022: 10; 2023: 8; 2024: 10; 2025: 2; 2026: 5.

44 papers.

Sort:

  1. 2024Parameter-Efficient Fine-Tuning with Discrete Fourier Transformcited by 67
  2. 2023Frequency Perception Network for Camouflaged Object Detectioncited by 37
  3. 2021TCGL: Temporal Contrastive Graph for Self-supervised Video Representation Learningcited by 31
  4. 2022Privacy-Preserving Face Recognition with Learnable Privacy Budgets in Frequency Domaincited by 28
  5. 2022Learning Spatiotemporal Frequency-Transformer for Compressed Video Super-Resolutioncited by 25
  6. 2021A Survey of Deep Learning Techniques for Weed Detection from Imagescited by 23
  7. 2023TransFace++: Rethinking the Face Recognition Paradigm with a Focus on Accuracy, Efficiency, and Securitycited by 22
  8. 2021Towards Discriminative Representation Learning for Unsupervised Person Re-identificationcited by 20
  9. 2022RGB no more: Minimally-decoded JPEG Vision Transformerscited by 18
  10. 2024Continual Learning in the Frequency Domaincited by 12
  11. 2021FreqNet: A Frequency-domain Image Super-Resolution Network with Dicrete Cosine Transformcited by 11
  12. 2022Boosting Night-time Scene Parsing with Learnable Frequencycited by 9
32 more
  1. 2024Latent-INR: A Flexible Framework for Implicit Representations of Videos with Discriminative Semanticscited by 9
  2. 2022Compressed Vision for Efficient Video Understandingcited by 8
  3. 2023Frequency Spectrum is More Effective for Multimodal Representation and Fusion: A Multimodal Spectrum Rumor Detectorcited by 8
  4. 2021Less is More: Accelerating Faster Neural Networks Straight from JPEGcited by 7
  5. 2021Prior-Induced Information Alignment for Image Mattingcited by 6
  6. 2023Machine Perception-Driven Image Compression: A Layered Generative Approachcited by 6
  7. 2023Lite-Mind: Towards Efficient and Robust Brain Representation Networkcited by 6
  8. 2024MaCP: Minimal yet Mighty Adaptation via Hierarchical Cosine Projectioncited by 6
  9. 2022FreeGaze: Resource-efficient Gaze Estimation via Frequency Domain Contrastive Learningcited by 5
  10. 2022Few-shot Fine-grained Image Classification via Multi-Frequency Neighborhood and Double-cross Modulationcited by 4
  11. 2024Constrained Multiview Representation for Self-supervised Contrastive Learningcited by 3
  12. 2021Efficient Visual Recognition with Deep Neural Networks: A Survey on Recent Advances and New Directionscited by 2
  13. 2024Learned Compression for Compressed Learningcited by 2
  14. 2026Bitstream Action Recognition is Byte Modelingcited by 2
  15. 2021Fake Visual Content Detection Using Two-Stream Convolutional Neural Networkscited by 1
  16. 2021Deep Learning Based Image Retrieval in the JPEG Compressed Domaincited by 1
  17. 2022Explicitly Increasing Input Information Density for Vision Transformers on Small Datasetscited by 1
  18. 2022Learning Spatiotemporal Frequency-Transformer for Low-Quality Video Super-Resolutioncited by 1
  19. 2023Learned Lossless Compression for JPEG via Frequency-Domain Predictioncited by 1
  20. 2026S2FT: Parameter-Efficient Fine-Tuning in Sparse Spectrum Domaincited by 1
  21. 2022Document Image Binarization in JPEG Compressed Domain using Dual Discriminator Generative Adversarial Networkscited by 0
  22. 2023CompTLL-UNet: Compressed Domain Text-Line Localization in Challenging Handwritten Documents using Deep Feature Learning from JPEG Coefficientscited by 0
  23. 2023CNNs for JPEGs: A Study in Computational Costcited by 0
  24. 2024Adaptive Hybrid Masking Strategy for Privacy-Preserving Face Recognition Against Model Inversion Attackcited by 0
  25. 2024Evaluating Adversarial Robustness in the Spatial Frequency Domaincited by 0
  26. 2024What Operations can be Performed Directly on Compressed Arrays, and with What Error?cited by 0
  27. 2024Content-Aware Preserving Image Generationcited by 0
  28. 2025MaCP: Minimal yet Mighty Adaptation via Hierarchical Cosine Projectioncited by 0
  29. 2025Learning Single-Image Super-Resolution in the JPEG Compressed Domaincited by 0
  30. 2026Low-Frequency Shortcuts in Texture-Driven Visual Learningcited by 0
  31. 2026SEAOTTER: Sensor Embedded Autoencoding with One-Time Transcode for Efficient Reconstructioncited by 0
  32. 2026FrequencyFormer: A Co-Designed Sensor-to-Processor Pipeline for Frequency-Domain Vision Transformer Inferencecited by 0