FUSE: Frequency-domain Unification and Spectral Energy Alignment for Multi-modal Object Re-Identification

• URL: http://arxiv.org/abs/2606.20044v1
• Date: Thu, 18 Jun 2026 10:21:32 GMT
• Title: FUSE: Frequency-domain Unification and Spectral Energy Alignment for Multi-modal Object Re-Identification
• Abstract summary: We introduce FUSE, a frequency-domain framework that reformulates multi-modal ReID as a two-stage process of spectral disentanglement and energy alignment.<n>The proposed Spectral Decomposition Module adaptively partitions features into low, mid, and high-frequency subspaces.<n>Experiments on RGBNT201, RGBNT100, and MSVR310 show that FUSE achieves 9.1% mAP and 9.5% Rank-1 improvements.
• Score: 41.52868809663972
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Despite significant progress in multi-modal Re-Identification (ReID), existing methods tend to emphasize low-frequency cues. Consequently, they focus on attributes such as color, illumination, and coarse appearance, while overlooking mid and high-frequency structures that encode geometric, textural, and identity-discriminative details. This imbalance leads to incomplete spectral representations and unstable cross-modal alignment. To overcome these limitations, we introduce FUSE, a frequency-domain framework that reformulates multi-modal ReID as a two-stage process of spectral disentanglement and energy alignment. The proposed Spectral Decomposition Module (SDM) adaptively partitions features into low, mid, and high-frequency subspaces, enabling hierarchical spectral modeling. The Cross-Modal Alignment Module (CAM) further enforces energy alignment and subspace complementarity across modalities via frequency-consistency regularization. In addition, FUSE incorporates learnable frequency modulation to enhance robustness under varying illumination and heterogeneous sensor conditions. Extensive experiments on RGBNT201, RGBNT100, and MSVR310 show that FUSE achieves 9.1\% mAP and 9.5\% Rank-1 improvements, establishing an interpretable frequency-domain paradigm for multi-modal representation learning.

Related papers

• FSCM: Frequency-Enhanced Spatial-Spectral Coupled Mamba for Infrared Hyperspectral Image Colorization [10.509841173943387]
  This paper presents a spectral-information-guided GAN framework for infrared colorization.<n>Within FSCM, a frequency-enhanced spatial-spectral state-space generator composed of cascaded FSB units is constructed.<n>Experiments show that FSCM outperforms existing infrared colorization methods in visual quality and semantic fidelity.
  arXiv  Detail & Related papers  (2026-05-13T15:48:58Z)
• Phy-CoSF: Physics-Guided Continuous Spectral Fields Reconstruction and Super-Resolution for Snapshot Compressive Imaging [79.35520607451187]
  We propose Phy-CoSF, which synergizes deep unfolding networks with implicit neural representations.<n>Specifically, we propose a two-phase architecture that bridges discrete-wavelength training with continuous spectral rendering.
  arXiv  Detail & Related papers  (2026-05-13T14:17:02Z)
• SpectralMamba-UNet: Frequency-Disentangled State Space Modeling for Texture-Structure Consistent Medical Image Segmentation [14.42559964239819]
  We propose SpectralMamba-UNet to decouple the learning of structural and textural information in the spectral domain.<n> Experiments on five public benchmarks demonstrate consistent improvements across diverse modalities and segmentation targets.
  arXiv  Detail & Related papers  (2026-02-26T15:17:42Z)
• Structured Spectral Reasoning for Frequency-Adaptive Multimodal Recommendation [13.886659472425393]
  Multimodal recommendation aims to integrate collaborative signals with heterogeneous content such as visual and textual information.<n>These issues are often exacerbated by naive fusion or shallow modeling strategies, leading to degraded generalization and poor robustness.<n>We propose a Structured Spectral Reasoning framework for frequency-aware multimodal recommendation.
  arXiv  Detail & Related papers  (2025-12-01T07:39:28Z)
• Frequency-Domain Decomposition and Recomposition for Robust Audio-Visual Segmentation [60.9960601057956]
  We introduce Frequency-Aware Audio-Visualcomposer (FAVS) framework consisting of two key modules.<n>FAVS framework achieves state-of-the-art performance on three benchmark datasets.
  arXiv  Detail & Related papers  (2025-09-23T12:33:48Z)
• SpectrumFM: Redefining Spectrum Cognition via Foundation Modeling [65.65474629224558]
  We propose a spectrum foundation model, termed SpectrumFM, which provides a new paradigm for spectrum cognition.<n>An innovative spectrum encoder that exploits the convolutional neural networks is proposed to effectively capture both fine-grained local signal structures and high-level global dependencies in the spectrum data.<n>Two novel self-supervised learning tasks, namely masked reconstruction and next-slot signal prediction, are developed for pre-training SpectrumFM, enabling the model to learn rich and transferable representations.
  arXiv  Detail & Related papers  (2025-08-02T14:40:50Z)
• FAD: Frequency Adaptation and Diversion for Cross-domain Few-shot Learning [35.40065954148091]
  Cross-domain few-shot learning requires models to generalize from limited labeled samples under significant distribution shifts.<n>We introduce Frequency Adaptation and Diversion (FAD), a frequency-aware framework that explicitly models and modulates spectral components.<n>FAD consistently outperforms state-of-the-art methods on both seen and unseen domains.
  arXiv  Detail & Related papers  (2025-05-13T08:48:06Z)
• PAD: Phase-Amplitude Decoupling Fusion for Multi-Modal Land Cover Classification [49.37555541088792]
  Phase-Amplitude Decoupling (PAD) is a frequency-aware framework that separates phase (modality-shared) and amplitude (modality-complementary) components.<n>This work establishes a new paradigm for physics-aware multi-modal fusion in remote sensing.
  arXiv  Detail & Related papers  (2025-04-27T07:21:42Z)
• Frequency Domain Modality-invariant Feature Learning for Visible-infrared Person Re-Identification [79.9402521412239]
  We propose a novel Frequency Domain modality-invariant feature learning framework (FDMNet) to reduce modality discrepancy from the frequency domain perspective. Our framework introduces two novel modules, namely the Instance-Adaptive Amplitude Filter (IAF) and the Phrase-Preserving Normalization (PPNorm)
  arXiv  Detail & Related papers  (2024-01-03T17:11:27Z)

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.