# Cross-architecture universal feature coding via distribution alignment

Source: [Cross-architecture universal feature coding via distribution alignment](<https://www.sota2.com/research/paper/68fa79681e209131cea7d760>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T04:57:49.425Z

Authors: Changsheng Gao, Shan Liu, Feng Wu, Weisi Lin

Published: 2025-06-15T06:14:02.000Z

## Abstract

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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2506.12737>)

[PDF](<https://arxiv.org/pdf/2506.12737.pdf>)
