Lune

CVPR Findings2026

What and Where to Adapt: Structure–Semantics Co-Tuning for Machine Vision Compression via Synergistic Adapters

Shaobo Liu, Haobo Xiong, Kai Liu, Yuna Lin

Abstract

Parameter-efficient fine-tuning of pre-trained codecs is a promising direction in image compression for human and machine vision. While most existing works have primarily focused on tuning the feature structure within the encoderdecoder backbones, the adaptation of the statistical semantics within the entropy model has received limited attention despite its function of predicting the probability distribution of latent features. Our analysis reveals that naive adapter insertion into the entropy model can lead to suboptimal outcomes, underscoring that the effectiveness of adapter-based tuning depends critically on the coordination between adapter type and placement across the compression pipeline. Therefore, we introduce Structure-Semantics Co-Tuning (S 2 -CoT), a novel framework that achieves this coordination via two specialized, synergistic adapters: the Structural Fidelity Adapter (SFA) and the Semantic Context Adapter (SCA). SFA is integrated into the encoder-decoder to preserve high-fidelity representations by dynamically fusing spatial and frequency information; meanwhile, the SCA adapts the entropy model to align with SFA-tuned features by refining the channel context for more efficient statistical coding. Through joint optimization, S 2 -CoT turns potential performance degradation into synergistic gains, achieving state-of-the-art results across four diverse base codecs with only a small fraction of trainable parameters, closely matching full fine-tuning performance. Code is available at https://github.com/Brock-bit4/S2-CoT.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Transformer-based Transform Coding cites Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
  • AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition cites Swin Transformer: Hierarchical Vision Transformer using Shifted Windows
  • AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition cites Towards a Unified View of Parameter-Efficient Transfer Learning
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on17

  1. Swin Transformer: Hierarchical Vision Transformer using Shifted WindowsZe Liu, Yutong Lin, Yue Cao, Han Hu et al.ICCV 2021 · 31,683 citations
  2. AdaptFormer: Adapting Vision Transformers for Scalable Visual RecognitionShoufa Chen, Chongjian Ge, Zhan Tong, Jiangliu Wang et al.NeurIPS 2022 · 1,291 citations
  3. Towards a Unified View of Parameter-Efficient Transfer LearningJunxian He, Chunting Zhou, Xuezhe Ma, Taylor Berg-Kirkpatrick et al.ICLR 2022 · 1,182 citations
  4. ELIC: Efficient Learned Image Compression with Unevenly Grouped Space-Channel Contextual Adaptive CodingDailan He, Ziming Yang, Weikun Peng, Rui Ma et al.CVPR 2022 · 363 citations
  5. Transformer-based Transform CodingYinhao Zhu, Yang Yang, Taco CohenICLR 2022 · 218 citations

Related papers

  1. Not All Directions Matter: Towards Structured and Task-Aware Low-Rank Model AdaptationXi Xiao, Chenrui Ma, Yunbei Zhang, Chen Liu et al.ACL 2026 · 6 citations
  2. Beyond Static Allocation: Dynamic Sensitivity-Aware Fine-Tuning for Vision TransformersYuanyang Cao, Xichun Liu, Fuwei Zhang, Shangqi Deng et al.ICML 2026
  3. One Adapter for All Programming Languages? Adapter Tuning for Code Search and SummarizationDeze Wang, Boxing Chen, Shanshan Li, Wei Luo et al.ICSE 2023 · 43 citations
  4. Sensitivity-Aware Efficient Fine-Tuning via Compact Dynamic-Rank AdaptationTianran Chen, Jiarui Chen, Baoquan Zhang, Zhehao Yu et al.CVPR 2025
  5. Sensitivity-Aware Visual Parameter-Efficient Fine-TuningHaoyu He, Jianfei Cai, Jing Zhang, Dacheng Tao et al.ICCV 2023 · 97 citations
Dusk over the sea between two cliffs drawn in fine vertical lines