CrossMambaTuning: Synergistic Spatial and Cross-Layer Adaptation for Machine Vision Compression

• URL: http://arxiv.org/abs/2608.25568v1
• Date: Wed, 26 Aug 2026 09:20:57 GMT
• Title: CrossMambaTuning: Synergistic Spatial and Cross-Layer Adaptation for Machine Vision Compression
• Abstract summary: We propose a novel framework named CrossMambaTuning, which integrates State Space Models with cross-layer interaction mechanisms for parameter-efficient fine-tuning.<n>Specifically, we design an efficient Mamba adapter equipped with task-specific prompts and multi-scale branching to precisely capture both local features and global dependencies.<n>Experiments demonstrate that CrossMambaTuning achieves state-of-the-art (SOTA) performance on multiple machine vision tasks, reducing parameter overhead by 72% compared to SOTA methods.
• Score: 4.294434416475728
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: To reduce deployment cost and retraining overhead, adapting pretrained learned image compression (LIC) models to downstream machine vision tasks has attracted growing attention. However, existing methods typically insert fine-tuning modules independently into frozen backbones, lacking explicit mechanisms for cross-layer coordination. To address this limitation, we propose a novel framework named CrossMambaTuning, which integrates State Space Models with cross-layer interaction mechanisms for parameter-efficient fine-tuning. Specifically, we design an efficient Mamba adapter equipped with task-specific prompts and multi-scale branching to precisely capture both local features and global dependencies. Furthermore, we introduce a Scale-Invariant Cross-Layer Adapter (SICA) utilizing a parameter-sharing strategy to fuse task information across different scales and reduce redundancy. Extensive experiments demonstrate that CrossMambaTuning achieves state-of-the-art (SOTA) performance on multiple machine vision tasks, reducing parameter overhead by 72\% compared to SOTA methods. Code is available at https://github.com/rsr1123/CrossMambaTuning.

Related papers

• MoECodec: Image Compression for joint human and machine perception via Mixture-of-Experts [37.49087932678935]
  MoECodec is a token-aware image compression framework that supports multiple downstream tasks within a single model.<n>MoECodec replaces the FFN layers in transformer-based compression model token-wise Mixture-of-Experts (MoE)
  arXiv  Detail & Related papers  (2026-06-19T01:56:25Z)
• Auto-FlexSwitch: Efficient Dynamic Model Merging via Learnable Task Vector Compression [54.12624130407679]
  We propose T-Switch, which decomposes task vectors into three compact components.<n>We then introduce Auto-Switch, a training-free merging scheme that automatically composes task vectors.<n>We present Auto-FlexSwitch, a dynamic model merging approach that supports highly efficient task vector compression.
  arXiv  Detail & Related papers  (2026-04-30T16:58:05Z)
• Parameter-Efficient Modality-Balanced Symmetric Fusion for Multimodal Remote Sensing Semantic Segmentation [8.840077295284393]
  MoBaNet is a parameter-efficient and modality-balanced symmetric fusion framework.<n>Built upon a largely frozen VFM backbone, MoBaNet adopts a symmetric dual-stream architecture to preserve generalizable representations.<n>Experiments on the ISPRS Vaihingen and Potsdam benchmarks demonstrate that MoBaNet achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2026-03-18T13:23:58Z)
• Parameter Aware Mamba Model for Multi-task Dense Prediction [69.94454603308196]
  We introduce a novel decoder-based framework, Aware Mamba Model (PAMM), specifically designed for dense prediction in multi-task learning setting.<n>It features dual state space parameter experts that integrate and set task-specific parameter priors, capturing the intrinsic properties of each task.<n>We employ the Multi-Directional Hilbert Scanning method to construct multi-angle feature sequences, thereby enhancing the sequence model's perceptual capabilities for 2D data.
  arXiv  Detail & Related papers  (2025-11-18T13:48:00Z)
• Structural Similarity-Inspired Unfolding for Lightweight Image Super-Resolution [88.20464308588889]
  We propose a Structural Similarity-Inspired Unfolding (SSIU) method for efficient image SR.<n>This method is designed through unfolding an SR optimization function constrained by structural similarity.<n>Our model outperforms current state-of-the-art models, boasting lower parameter counts and reduced memory consumption.
  arXiv  Detail & Related papers  (2025-06-13T14:29:40Z)
• Multi-Level Embedding and Alignment Network with Consistency and Invariance Learning for Cross-View Geo-Localization [2.733505168507872]
  Cross-View Geo-Localization (CVGL) involves determining the localization of drone images by retrieving the most similar GPS-tagged satellite images.<n>Existing methods often overlook the problem of increased computational and storage requirements when improving model performance.<n>We propose a lightweight enhanced alignment network, called the Multi-Level Embedding and Alignment Network (MEAN)
  arXiv  Detail & Related papers  (2024-12-19T13:10:38Z)
• SparX: A Sparse Cross-Layer Connection Mechanism for Hierarchical Vision Mamba and Transformer Networks [45.68176825375723]
  This paper introduces an efficient cross-layer feature aggregation mechanism for vision backbone networks.<n>Inspired by the Retinal Ganglion Cells (RGCs) in the human visual system, we propose a new sparse cross-layer connection mechanism termed SparX.<n>Our new connection mechanism possesses both superior performance and generalization capabilities on various vision tasks.
  arXiv  Detail & Related papers  (2024-09-15T07:46:18Z)
• CAS-ViT: Convolutional Additive Self-attention Vision Transformers for Efficient Mobile Applications [73.80247057590519]
  Vision Transformers (ViTs) mark a revolutionary advance in neural networks with their token mixer's powerful global context capability.<n>We introduce CAS-ViT: Convolutional Additive Self-attention Vision Transformers, to achieve a balance between efficiency and performance in mobile applications.<n>Our model achieves 83.0%/84.1% top-1 with only 12M/21M parameters on ImageNet-1K.
  arXiv  Detail & Related papers  (2024-08-07T11:33:46Z)
• SHERL: Synthesizing High Accuracy and Efficient Memory for Resource-Limited Transfer Learning [63.93193829913252]
  We propose an innovative METL strategy called SHERL for resource-limited scenarios. In the early route, intermediate outputs are consolidated via an anti-redundancy operation. In the late route, utilizing minimal late pre-trained layers could alleviate the peak demand on memory overhead.
  arXiv  Detail & Related papers  (2024-07-10T10:22:35Z)
• Consolidator: Mergeable Adapter with Grouped Connections for Visual Adaptation [53.835365470800916]
  We show how to efficiently and effectively transfer knowledge in a vision transformer. We propose consolidator to modify the pre-trained model with the addition of a small set of tunable parameters. Our consolidator can reach up to 7.56 better accuracy than full fine-tuning with merely 0.35% parameters.
  arXiv  Detail & Related papers  (2023-04-30T23:59:02Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.