Progressive Learned Image Compression for Machine Perception
Not on the map. Why?
Abstract (arXiv)
Recent advances in learned image codecs have extended from human perception toward machine perception However, progressive image compression with fine granular scalability (FGS)-which enables decoding a single bitstream at multiple quality levels-remains unexplored for machine-oriented codecs. In this work, we propose PICM-Net, a progressive learned image compression codec for machine perception built on trit-plane coding. Starting from a human-oriented codec, we adapt it for machine perception via a spatial-frequency modulation adapter (SFMA), a hyper-synthesis low-rank adapter (HSLoRA), and progressive decoding-aware training, and analyze how task-driven adaptation alters symbol prioritization for progressive transmission. To further support real-world deployment, we introduce an adaptive decoding controller that dynamically determines the necessary decoding level at inference time, requesting additional bits only when the current suitability is insufficient for the desired confidence level. Extensive experiments demonstrate that PICM-Net achieves efficient and adaptive progressive transmission while maintaining strong downstream classification performance. Our code is available at https://github.com/kjungwoo03/PICM-Net.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 53 of its 80 references that are in the map. First posted on arXiv 23 Dec 2025.
Builds on
53 of 80 references.
References · 53
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
- 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
- 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
- 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
- 2020End-to-End Object Detection with Transformerscited by 7,414
- 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
- 2017On Calibration of Modern Neural Networkscited by 4,960
- 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,859
- 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,852
- 2022A ConvNet for the 2020scited by 3,579
- 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,223
38 more
- 2018UNet++: A Nested U-Net Architecture for Medical Image Segmentationcited by 1,525
- 2018Variational image compression with a scale hyperpriorcited by 935
- 2018Joint Autoregressive and Hierarchical Priors for Learned Image Compressioncited by 664
- 2020Learned Image Compression with Discretized Gaussian Mixture Likelihoods and Attention Modulescited by 590
- 2023End-to-end Autonomous Driving: Challenges and Frontierscited by 490
- 2022ELIC: Efficient Learned Image Compression with Unevenly Grouped Space-Channel Contextual Adaptive Codingcited by 301
- 2020CompressAI: a PyTorch library and evaluation platform for end-to-end compression researchcited by 276
- 2023Learned Image Compression with Mixed Transformer-CNN Architecturescited by 211
- 2022The Devil Is in the Details: Window-based Attention for Image Compressioncited by 147
- 2018Context-adaptive Entropy Model for End-to-end Optimized Image Compressioncited by 143
- 2021Predicting with Confidence on Unseen Distributionscited by 116
- 2025Don't Shake the Wheel: Momentum-Aware Planning in End-to-End Autonomous Drivingcited by 84
- 2021Transformer-based Image Compressioncited by 62
- 2022Part-based Pseudo Label Refinement for Unsupervised Person Re-identificationcited by 59
- 2021Joint Global and Local Hierarchical Priors for Learned Image Compressioncited by 54
- 2021Image coding for machines: an end-to-end learned approachcited by 47
- 2023Towards Surveillance Video-and-Language Understanding: New Dataset, Baselines, and Challengescited by 42
- 2023TransTIC: Transferring Transformer-based Image Compression from Human Perception to Machine Perceptioncited by 32
- 2022Image Coding for Machines with Omnipotent Feature Learningcited by 31
- 2024Image Compression for Machine and Human Vision with Spatial-Frequency Adaptationcited by 26
- 2025OSCAR: One-Step Diffusion Codec Across Multiple Bit-ratescited by 26
- 2021DPICT: Deep Progressive Image Compression Using Trit-Planescited by 25
- 2021Progressive Neural Image Compression with Nested Quantization and Latent Orderingcited by 24
- 2023Confidence and Dispersity Speak: Characterising Prediction Matrix for Unsupervised Accuracy Estimationcited by 22
- 2023Context-Based Trit-Plane Coding for Progressive Image Compressioncited by 21
- 2025MambaIC: State Space Models for High-Performance Learned Image Compressioncited by 20
- 2024Image Coding for Machines with Edge Information Learning Using Segment Anythingcited by 17
- 2024Once-for-All: Controllable Generative Image Compression with Dynamic Granularity Adaptationcited by 16
- 2024All-in-One Image Coding for Joint Human-Machine Vision with Multi-Path Aggregationcited by 14
- 2023ProgDTD: Progressive Learned Image Compression with Double-Tail-Drop Trainingcited by 13
- 2024Rate-Distortion-Cognition Controllable Versatile Neural Image Compressioncited by 11
- 2023ROI-based Deep Image Compression with Swin Transformerscited by 10
- 2024Progressive Compression with Universally Quantized Diffusion Modelscited by 10
- 2024DeepHQ: Learned Hierarchical Quantizer for Progressive Deep Image Codingcited by 5
- 2023Toward Auto-evaluation with Confidence-based Category Relation-aware Regressioncited by 4
- 2024Efficient Progressive Image Compression with Variance-aware Maskingcited by 4
- 2025Suitability Filter: A Statistical Framework for Classifier Evaluation in Real-World Deployment Settingscited by 4
- 2025Explicit Residual-Based Scalable Image Coding for Humans and Machinescited by 3
50 most cited of 53 All 53 (JSON)
Built on by
Citing papers per year: 2026: 1.
1 paper.