# All-in-One Image Coding for Joint Human-Machine Vision with Multi-Path Aggregation

arXiv: https://arxiv.org/abs/2409.19660 · HTML: https://mlsanity.com/paper/2409.19660/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- Builds on 54 of its 80 references that are in the map.
- First posted on arXiv 29 Sep 2024.

## Builds on (most cited first, 30 of 54)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [A ConvNet for the 2020s](https://mlsanity.com/paper/2201.03545/) (2022)
- [Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer](https://mlsanity.com/paper/1701.06538/) (2017)
- [Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity](https://mlsanity.com/paper/2101.03961/) (2021)
- [Categorical Reparameterization with Gumbel-Softmax](https://mlsanity.com/paper/1611.01144/) (2016)
- [Pyramid Scene Parsing Network](https://mlsanity.com/paper/1612.01105/) (2016)
- [Visual Prompt Tuning](https://mlsanity.com/paper/2203.12119/) (2022)
- [GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding](https://mlsanity.com/paper/2006.16668/) (2020)
- [Swin Transformer V2: Scaling Up Capacity and Resolution](https://mlsanity.com/paper/2111.09883/) (2021)
- [Semantic Understanding of Scenes through the ADE20K Dataset](https://mlsanity.com/paper/1608.05442/) (2016)
- [GLaM: Efficient Scaling of Language Models with Mixture-of-Experts](https://mlsanity.com/paper/2112.06905/) (2021)
- [Multi-Task Learning as Multi-Objective Optimization](https://mlsanity.com/paper/1810.04650/) (2018)
- [Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Tasks](https://mlsanity.com/paper/2208.10442/) (2022)
- [VLMo: Unified Vision-Language Pre-Training with Mixture-of-Modality-Experts](https://mlsanity.com/paper/2111.02358/) (2021)
- [High-Fidelity Generative Image Compression](https://mlsanity.com/paper/2006.09965/) (2020)
- [CompressAI: a PyTorch library and evaluation platform for end-to-end compression research](https://mlsanity.com/paper/2011.03029/) (2020)
- [AdaViT: Adaptive Vision Transformers for Efficient Image Recognition](https://mlsanity.com/paper/2111.15668/) (2021)
- [Pareto Multi-Task Learning](https://mlsanity.com/paper/1912.12854/) (2019)
- [Learned Image Compression with Mixed Transformer-CNN Architectures](https://mlsanity.com/paper/2303.14978/) (2023)
- [Full-Gradient Representation for Neural Network Visualization](https://mlsanity.com/paper/1905.00780/) (2019)

## Built on by (most cited first, 14 of 14)

- [SLIM: Semantic-based Low-bitrate Image compression for Machines by leveraging diffusion](https://mlsanity.com/paper/2512.18200/) (2025)
- [Leveraging Diffusion Knowledge for Generative Image Compression with Fractal Frequency-Aware Band Learning](https://mlsanity.com/paper/2503.11321/) (2025)
- [Perception-Oriented Latent Coding for High-Performance Compressed Domain Semantic Inference](https://mlsanity.com/paper/2507.01608/) (2025)
- [Machines Serve Human: A Novel Variable Human-machine Collaborative Compression Framework](https://mlsanity.com/paper/2511.08915/) (2025)
- [Progressive Learned Image Compression for Machine Perception](https://mlsanity.com/paper/2512.20070/) (2025)
- [Towards Large Model Feature Coding](https://mlsanity.com/paper/2605.24025/) (2026)
- [UniTAC: Universal Task-Aware Compression via Weighted Distortion Measures](https://mlsanity.com/paper/2608.16696/) (2026)
- [Generative Semantic Coding for Ultra-Low Bitrate Visual Communication and Analysis](https://mlsanity.com/paper/2510.27324/) (2025)
- [Multi-task Just Recognizable Difference for Video Coding for Machines: Database, Model, and Coding Application](https://mlsanity.com/paper/2604.09421/) (2026)
- [What and Where to Adapt: Structure-Semantics Co-Tuning for Machine Vision Compression via Synergistic Adapters](https://mlsanity.com/paper/2604.10017/) (2026)
- [PAT-VCM: Plug-and-Play Auxiliary Tokens for Video Coding for Machines](https://mlsanity.com/paper/2604.13294/) (2026)
- [Coarse-to-Fine: Progressive Image Compression for Semantically Hierarchical Classification](https://mlsanity.com/paper/2605.08266/) (2026)
- [MoECodec: Image Compression for joint human and machine perception via Mixture-of-Experts](https://mlsanity.com/paper/2606.21033/) (2026)
- [CrossMambaTuning: Synergistic Spatial and Cross-Layer Adaptation for Machine Vision Compression](https://mlsanity.com/paper/2608.25568/) (2026)

## Abstract (arXiv)

Image coding for multi-task applications, catering to both human perception and machine vision, has been extensively investigated. Existing methods often rely on multiple task-specific encoder-decoder pairs, leading to high overhead of parameter and bitrate usage, or face challenges in multi-objective optimization under a unified representation, failing to achieve both performance and efficiency. To this end, we propose Multi-Path Aggregation (MPA) integrated into existing coding models for joint human-machine vision, unifying the feature representation with an all-in-one architecture. MPA employs a predictor to allocate latent features among task-specific paths based on feature importance varied across tasks, maximizing the utility of shared features while preserving task-specific features for subsequent refinement. Leveraging feature correlations, we develop a two-stage optimization strategy to alleviate multi-task performance degradation. Upon the reuse of shared features, as low as 1.89% parameters are further augmented and fine-tuned for a specific task, which completely avoids extensive optimization of the entire model. Experimental results show that MPA achieves performance comparable to state-of-the-art methods in both task-specific and multi-objective optimization across human viewing and machine analysis tasks. Moreover, our all-in-one design supports seamless transitions between human- and machine-oriented reconstruction, enabling task-controllable interpretation without altering the unified model. Code is available at https://github.com/NJUVISION/MPA.