mlsanityData to 14 Oct 2026

Frequency-Aware Transformer for Learned Image Compression

arXiv 2310.16387 ↗First posted 25 Oct 2023eess.IV cs.CVcited by 58

Not on the map. Why?

Abstract (arXiv)

Learned image compression (LIC) has gained traction as an effective solution for image storage and transmission in recent years. However, existing LIC methods are redundant in latent representation due to limitations in capturing anisotropic frequency components and preserving directional details. To overcome these challenges, we propose a novel frequency-aware transformer (FAT) block that for the first time achieves multiscale directional ananlysis for LIC. The FAT block comprises frequency-decomposition window attention (FDWA) modules to capture multiscale and directional frequency components of natural images. Additionally, we introduce frequency-modulation feed-forward network (FMFFN) to adaptively modulate different frequency components, improving rate-distortion performance. Furthermore, we present a transformer-based channel-wise autoregressive (T-CA) model that effectively exploits channel dependencies. Experiments show that our method achieves state-of-the-art rate-distortion performance compared to existing LIC methods, and evidently outperforms latest standardized codec VTM-12.1 by 14.5%, 15.1%, 13.0% in BD-rate on the Kodak, Tecnick, and CLIC datasets.

Key facts. Cited by 58 papers in the map (data through 14 Oct 2026). Builds on 25 of its 40 references that are in the map. First posted on arXiv 25 Oct 2023.

Builds on

25 of 40 references.

References · 25

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  4. 2020End-to-End Object Detection with Transformerscited by 7,414
  5. 2018Variational image compression with a scale hyperpriorcited by 935
  6. 2018Joint Autoregressive and Hierarchical Priors for Learned Image Compressioncited by 664
  7. 2020Learned Image Compression with Discretized Gaussian Mixture Likelihoods and Attention Modulescited by 590
  8. 2022How Do Vision Transformers Work?cited by 307
  9. 2022ELIC: Efficient Learned Image Compression with Unevenly Grouped Space-Channel Contextual Adaptive Codingcited by 301
  10. 2020CompressAI: a PyTorch library and evaluation platform for end-to-end compression researchcited by 276
  11. 2020Channel-wise Autoregressive Entropy Models for Learned Image Compressioncited by 264
  12. 2021Global Filter Networks for Image Classificationcited by 260
13 more
  1. 2023Learned Image Compression with Mixed Transformer-CNN Architecturescited by 211
  2. 2022The Devil Is in the Details: Window-based Attention for Image Compressioncited by 147
  3. 2022Entroformer: A Transformer-based Entropy Model for Learned Image Compressioncited by 107
  4. 2021Enhanced Invertible Encoding for Learned Image Compressioncited by 105
  5. 2022Fast Vision Transformers with HiLo Attentioncited by 78
  6. 2022VCT: A Video Compression Transformercited by 74
  7. 2021Transformer-based Image Compressioncited by 62
  8. 2020A Unified End-to-End Framework for Efficient Deep Image Compressioncited by 58
  9. 2021Motion-aware Contrastive Video Representation Learning via Foreground-background Mergingcited by 45
  10. 2022Contextformer: A Transformer with Spatio-Channel Attention for Context Modeling in Learned Image Compressioncited by 45
  11. 2023Pose-Oriented Transformer with Uncertainty-Guided Refinement for 2D-to-3D Human Pose Estimationcited by 19
  12. 2022Dual Contrastive Learning for Spatio-temporal Representationcited by 15
  13. 2023Frequency Disentangled Features in Neural Image Compressioncited by 14

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 7; 2025: 30; 2026: 20.

58 papers.

Sort:

By area:

  1. 2024Improving Diffusion Models for Inverse Problems Using Optimal Posterior Covariancecited by 44
  2. 2025Learned Image Compression with Dictionary-based Entropy Modelcited by 30
  3. 2024Image Compression for Machine and Human Vision with Spatial-Frequency Adaptationcited by 26
  4. 2024RDEIC: Accelerating Diffusion-Based Extreme Image Compression with Relay Residual Diffusioncited by 23
  5. 2025Linear Attention Modeling for Learned Image Compressioncited by 23
  6. 2025Learned Image Compression with Hierarchical Progressive Context Modelingcited by 21
  7. 2024Causal Context Adjustment Loss for Learned Image Compressioncited by 19
  8. 2025Large Language Model for Lossless Image Compression with Visual Promptscited by 16
  9. 2024Rate-Distortion-Cognition Controllable Versatile Neural Image Compressioncited by 11
  10. 2023Betrayed by Attention: A Simple yet Effective Approach for Self-supervised Video Object Segmentationcited by 10
  11. 2025Lossy Neural Compression for Geospatial Analytics: A Reviewcited by 10
  12. 2025HiPART: Hierarchical Pose AutoRegressive Transformer for Occluded 3D Human Pose Estimationcited by 8
38 more
  1. 2025Content-Aware Mamba for Learned Image Compressioncited by 6
  2. 2025Balanced Rate-Distortion Optimization in Learned Image Compressioncited by 5
  3. 2026Dual-Representation Image Compression at Ultra-Low Bitrates via Explicit Semantics and Implicit Texturescited by 5
  4. 2026Differentiable Vector Quantization for Rate-Distortion Optimization of Generative Image Compressioncited by 5
  5. 2024High Frequency Matters: Uncertainty Guided Image Compression with Wavelet Diffusioncited by 4
  6. 2025A Lightweight Model for Perceptual Image Compression via Implicit Priorscited by 4
  7. 2025Synonymous Variational Inference for Perceptual Image Compressioncited by 4
  8. 2025Diff-ICMH: Harmonizing Machine and Human Vision in Image Compression with Generative Priorcited by 4
  9. 2026Next-Frame Decoding for Ultra-Low-Bitrate Image Compression with Video Diffusion Priorscited by 3
  10. 20253DM-WeConvene: Learned Image Compression with 3D Multi-Level Wavelet-Domain Convolution and Entropy Modelcited by 2
  11. 2025Neural Stereo Video Compression with Hybrid Disparity Compensationcited by 2
  12. 2025Scaling Learned Image Compression Models up to 1 Billioncited by 2
  13. 2025Switchable Token-Specific Codebook Quantization For Face Image Compressioncited by 2
  14. 2026Compression Tells Intelligence: Visual Coding, Visual Token Technology, and the Unificationcited by 2
  15. 2026Leveraging Second-Order Curvature for Efficient Learned Image Compression: Theory and Empirical Evidencecited by 2
  16. 2024Rethinking Learned Image Compression: Context is All You Needcited by 1
  17. 2025Leveraging Diffusion Knowledge for Generative Image Compression with Fractal Frequency-Aware Band Learningcited by 1
  18. 2025All-in-One Transferring Image Compression from Human Perception to Multi-Machine Perceptioncited by 1
  19. 2025High Quality Underwater Image Compression with Adaptive Color Correctioncited by 1
  20. 2025Accelerating Learned Image Compression Through Modeling Neural Training Dynamicscited by 1
  21. 2025Neural Weight Compression for Language Modelscited by 1
  22. 2025BADiff: Bandwidth Adaptive Diffusion Modelcited by 1
  23. 2025Deeply-Conditioned Image Compression via Self-Generated Priorscited by 1
  24. 2026Uni-LVC: A Unified Method for Intra- and Inter-Mode Learned Video Compressioncited by 1
  25. 2026Inevitable Encounters: Backdoor Attacks Involving Lossy Compressioncited by 1
  26. 2026Adaptive Learned Image Compression with Graph Neural Networkscited by 1
  27. 2026Exploiting Semantic and Pixel Representations for Ultra-Low Bitrate Image Compressioncited by 1
  28. 2025S2CFormer: Revisiting the RD-Latency Trade-off in Transformer-based Learned Image Compressioncited by 0
  29. 2025FaSDiff: Balancing Perception and Semantics in Face Compression via Stable Diffusion Priorscited by 0
  30. 2025Comp-X: On Defining an Interactive Learned Image Compression Paradigm With Expert-driven LLM Agentcited by 0
  31. 2025TerraCodec: Compressing Optical Earth Observation Datacited by 0
  32. 2025FLaTEC: Frequency-Disentangled Latent Triplanes for Efficient Compression of LiDAR Point Cloudscited by 0
  33. 2025A Compact Hybrid Convolution--Frequency State Space Network for Learned Image Compressioncited by 0
  34. 2025SDGIC: A Semantic Disambiguation-Guided Generative Image Compression Method for Ultra-Low Bitratescited by 0
  35. 2025Error-Propagation-Free Learned Video Compression With Dual-Domain Progressive Temporal Alignmentcited by 0
  36. 2026Understanding Rate-Distortion Performance in Distributed Transformer Inferencecited by 0
  37. 2026HiDE: Hierarchical Dictionary-Based Entropy Modeling for Learned Image Compressioncited by 0
  38. 2026What and Where to Adapt: Structure-Semantics Co-Tuning for Machine Vision Compression via Synergistic Adapterscited by 0

50 most cited of 58 All 58 (JSON)