collaborators

5 papers

cs.CV2026

Visual Token Codec: Unleashing Spatial Redundancy for ViT Feature Coding

Donghui Feng, Fengxi Zhang, Changsheng Gao +6

Distributed deployment of large vision foundation models often partitions a ViT backbone and exchanges intermediate token features between computing nodes, making efficient feature…

cs.CV2026

Towards Large Model Feature Coding

Youwei Pang, Changsheng Gao, Dong Liu +2

Large models have delivered remarkable performance across a wide range of perception and generation tasks, yet practical deployment is increasingly constrained by computational and…

cs.MM2025

DT-UFC: Universal Large Model Feature Coding via Peaky-to-Balanced Distribution Transformation

Changsheng Gao, Zijie Liu, Li Li +3

Like image coding in visual data transmission, feature coding is essential for the distributed deployment of large models by significantly reducing transmission and storage burden.…

cs.CV2025

Compressed Feature Quality Assessment: Dataset and Baselines

Changsheng Gao, Wei Zhou, Guosheng Lin +1

The widespread deployment of large models in resource-constrained environments has underscored the need for efficient transmission of intermediate feature representations. In this…

cs.CV2025

Cross-architecture universal feature coding via distribution alignment

Changsheng Gao, Shan Liu, Feng Wu +1

Feature coding has become increasingly important in scenarios where semantic representations rather than raw pixels are transmitted and stored. However, most existing methods are a…