# Cross-architecture universal feature coding via distribution alignment

arXiv: https://arxiv.org/abs/2506.12737 · HTML: https://mlsanity.com/paper/2506.12737/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 26 references that are in the map.
- First posted on arXiv 15 Jun 2025.

## Builds on (most cited first, 11 of 11)

- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Variational image compression with a scale hyperprior](https://mlsanity.com/paper/1802.01436/) (2018)
- [Scalable Image Coding for Humans and Machines](https://mlsanity.com/paper/2107.08373/) (2021)
- [Deep feature compression for collaborative object detection](https://mlsanity.com/paper/1802.03931/) (2018)
- [Multi-task learning with compressible features for Collaborative Intelligence](https://mlsanity.com/paper/1902.05179/) (2019)
- [Bit Allocation for Multi-Task Collaborative Intelligence](https://mlsanity.com/paper/2002.07048/) (2020)
- [End-to-End Learnable Multi-Scale Feature Compression for VCM](https://mlsanity.com/paper/2306.16670/) (2023)
- [Feature Coding in the Era of Large Models: Dataset, Test Conditions, and Benchmark](https://mlsanity.com/paper/2412.04307/) (2024)
- [DMOFC: Discrimination Metric-Optimized Feature Compression](https://mlsanity.com/paper/2405.04044/) (2024)
- [Toward Scalable Image Feature Compression: A Content-Adaptive and Diffusion-Based Approach](https://mlsanity.com/paper/2410.06149/) (2024)
- [Compressed Feature Quality Assessment: Dataset and Baselines](https://mlsanity.com/paper/2506.07412/) (2025)

## Built on by (most cited first, 2 of 2)

- [Towards Large Model Feature Coding](https://mlsanity.com/paper/2605.24025/) (2026)
- [Visual Token Codec: Unleashing Spatial Redundancy for ViT Feature Coding](https://mlsanity.com/paper/2608.08832/) (2026)

## Abstract (arXiv)

Feature coding has become increasingly important in scenarios where semantic representations rather than raw pixels are transmitted and stored. However, most existing methods are architecture-specific, targeting either CNNs or Transformers. This design limits their applicability in real-world scenarios where features from both architectures coexist. To address this gap, we introduce a new research problem: cross-architecture universal feature coding (CAUFC), which seeks to build a unified codec that can effectively compress features from heterogeneous architectures. To tackle this challenge, we propose a two-step distribution alignment method. First, we design the format alignment method that unifies CNN and Transformer features into a consistent 2D token format. Second, we propose the feature value alignment method that harmonizes statistical distributions via truncation and normalization. As a first attempt to study CAUFC, we evaluate our method on the image classification task. Experimental results demonstrate that our method achieves superior rate-accuracy trade-offs compared to the architecture-specific baseline. This work marks an initial step toward universal feature compression across heterogeneous model architectures.