mlsanityData to 7 Oct 2026

Transformer-based Image Compression

arXiv 2111.06707 ↗First posted 12 Nov 2021eess.IV cs.CVcited by 60

Not on the map. Why?

Abstract (arXiv)

A Transformer-based Image Compression (TIC) approach is developed which reuses the canonical variational autoencoder (VAE) architecture with paired main and hyper encoder-decoders. Both main and hyper encoders are comprised of a sequence of neural transformation units (NTUs) to analyse and aggregate important information for more compact representation of input image, while the decoders mirror the encoder-side operations to generate pixel-domain image reconstruction from the compressed bitstream. Each NTU is consist of a Swin Transformer Block (STB) and a convolutional layer (Conv) to best embed both long-range and short-range information; In the meantime, a casual attention module (CAM) is devised for adaptive context modeling of latent features to utilize both hyper and autoregressive priors. The TIC rivals with state-of-the-art approaches including deep convolutional neural networks (CNNs) based learnt image coding (LIC) methods and handcrafted rules-based intra profile of recently-approved Versatile Video Coding (VVC) standard, and requires much less model parameters, e.g., up to 45% reduction to leading-performance LIC.

Key facts. Cited by 60 papers in the map (data through 7 Oct 2026). Builds on 17 of its 23 references that are in the map. First posted on arXiv 12 Nov 2021.

Builds on

17 of 23 references.

References · 17

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  4. 2020End-to-End Object Detection with Transformerscited by 7,384
  5. 2021SwinIR: Image Restoration Using Swin Transformercited by 1,869
  6. 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,838
  7. 2018Variational image compression with a scale hyperpriorcited by 910
  8. 2021Uformer: A General U-Shaped Transformer for Image Restorationcited by 864
  9. 2016End-to-end Optimized Image Compressioncited by 673
  10. 2018Joint Autoregressive and Hierarchical Priors for Learned Image Compressioncited by 642
  11. 2020Learned Image Compression with Discretized Gaussian Mixture Likelihoods and Attention Modulescited by 570
  12. 2017PixelCNN++: Improving the PixelCNN with Discretized Logistic Mixture Likelihood and Other Modificationscited by 415
5 more
  1. 2021Early Convolutions Help Transformers See Bettercited by 395
  2. 2021DeepViT: Towards Deeper Vision Transformercited by 288
  3. 2020CompressAI: a PyTorch library and evaluation platform for end-to-end compression researchcited by 271
  4. 2019Non-local Attention Optimized Deep Image Compressioncited by 86
  5. 2020A Unified End-to-End Framework for Efficient Deep Image Compressioncited by 56

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 5; 2023: 15; 2024: 11; 2025: 21; 2026: 7.

60 papers.

Sort:

By area:

  1. 2023Learned Image Compression with Mixed Transformer-CNN Architecturescited by 205
  2. 2022MLIC: Multi-Reference Entropy Model for Learned Image Compressioncited by 80
  3. 2023MLIC++: Linear Complexity Multi-Reference Entropy Modeling for Learned Image Compressioncited by 56
  4. 2023Frequency-Aware Transformer for Learned Image Compressioncited by 56
  5. 2022Lossy Image Compression with Quantized Hierarchical VAEscited by 32
  6. 2024MambaVC: Learned Visual Compression with Selective State Spacescited by 28
  7. 2024Image Compression for Machine and Human Vision with Spatial-Frequency Adaptationcited by 26
  8. 2021Towards Robust Neural Image Compression: Adversarial Attack and Model Finetuningcited by 24
  9. 2025Linear Attention Modeling for Learned Image Compressioncited by 22
  10. 2024Causal Context Adjustment Loss for Learned Image Compressioncited by 19
  11. 2022Efficient Visual Computing with Camera RAW Snapshotscited by 18
  12. 2025MambaIC: State Space Models for High-Performance Learned Image Compressioncited by 18
38 more
  1. 2025Ultra Lowrate Image Compression with Semantic Residual Coding and Compression-aware Diffusioncited by 17
  2. 2022High-Efficiency Lossy Image Coding Through Adaptive Neighborhood Information Aggregationcited by 16
  3. 2024All-in-One Image Coding for Joint Human-Machine Vision with Multi-Path Aggregationcited by 14
  4. 2023End-to-End Learnable Multi-Scale Feature Compression for VCMcited by 13
  5. 2023FrankenSplit: Efficient Neural Feature Compression with Shallow Variational Bottleneck Injection for Mobile Edge Computingcited by 12
  6. 2024Rate-Distortion-Cognition Controllable Versatile Neural Image Compressioncited by 11
  7. 2023ROI-based Deep Image Compression with Swin Transformerscited by 10
  8. 2023Dynamic Low-Rank Instance Adaptation for Universal Neural Image Compressioncited by 10
  9. 2023Transformer-based Variable-rate Image Compression with Region-of-interest Controlcited by 7
  10. 2023Image Coding for Machines with Object Region Learningcited by 7
  11. 2022Efficient LiDAR Point Cloud Geometry Compression Through Neighborhood Point Attentioncited by 6
  12. 2023LLIC: Large Receptive Field Transform Coding with Adaptive Weights for Learned Image Compressioncited by 6
  13. 2025Large Language Models as Computable Approximations to Solomonoff Inductioncited by 6
  14. 2025Content-Aware Mamba for Learned Image Compressioncited by 5
  15. 2023Progressive Learning with Visual Prompt Tuning for Variable-Rate Image Compressioncited by 3
  16. 2024NVC-1B: A Large Neural Video Coding Modelcited by 3
  17. 2025Customizable ROI-Based Deep Image Compressioncited by 3
  18. 2024SLIC: A Learned Image Codec Using Structure and Colorcited by 2
  19. 2024Wavelet-Like Transform-Based Technology in Response to the Call for Proposals on Neural Network-Based Image Codingcited by 2
  20. 2023Multi-spectral Entropy Constrained Neural Compression of Solar Imagerycited by 1
  21. 2023Transformer-based Image Compression with Variable Image Quality Objectivescited by 1
  22. 2024Domain Adaptation for Learned Image Compression with Supervised Adapterscited by 1
  23. 2024Rethinking Learned Image Compression: Context is All You Needcited by 1
  24. 2024An Information-Theoretic Regularizer for Lossy Neural Image Compressioncited by 1
  25. 2025Adjustable Spatio-Spectral Hyperspectral Image Compression Networkcited by 1
  26. 2025SEEC: Segmentation-Assisted Multi-Entropy Models for Learned Lossless Image Compressioncited by 1
  27. 2025Progressive Learned Image Compression for Machine Perceptioncited by 1
  28. 2026CADC: Content Adaptive Diffusion-Based Generative Image Compressioncited by 1
  29. 2026Viewport-based Neural 360deg Image Compressioncited by 1
  30. 2023Dynamic Kernel-Based Adaptive Spatial Aggregation for Learned Image Compressioncited by 0
  31. 2023Image Compression using only Attention based Neural Networkscited by 0
  32. 2025Learning Joint Denoising, Demosaicing, and Compression from the Raw Natural Image Noise Datasetcited by 0
  33. 2025S2CFormer: Revisiting the RD-Latency Trade-off in Transformer-based Learned Image Compressioncited by 0
  34. 2025Compact Latent Representation for Image Compression (CLRIC)cited by 0
  35. 2025Interleaved Block-based Learned Image Compression with Feature Enhancement and Quantization Error Compensationcited by 0
  36. 2025LoC-LIC: Low Complexity Learned Image Coding Using Hierarchical Feature Transformscited by 0
  37. 2025Optimizing Learned Image Compression on Scalar and Entropy-Constraint Quantizationcited by 0
  38. 2025Perception-Oriented Latent Coding for High-Performance Compressed Domain Semantic Inferencecited by 0

50 most cited of 60 All 60 (JSON)