MFEN:Multi-Frequency Expert Network for Visible-Infrared Person Re-ID

• URL: http://arxiv.org/abs/2606.12051v1
• Date: Wed, 10 Jun 2026 13:16:22 GMT
• Title: MFEN:Multi-Frequency Expert Network for Visible-Infrared Person Re-ID
• Abstract summary: Visible-infrared person re-identification (VI-ReID) is challenging due to the large modality discrepancy between visible and infrared images.<n>We propose a Multi-Frequency Expert Network (MFEN) that enables multi-frequency modulation and adaptively combines different bands.
• Score: 54.607429411644716
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Visible-infrared person re-identification (VI-ReID) is challenging due to the large modality discrepancy between visible and infrared images. We contend that this discrepancy is largely related to differing lighting conditions, including differences in light wavelength and light source type. Recently, frequency-based VI-ReID approaches have achieved notable success because frequency information can better extract identity-relevant contours and details while excluding irrelevant lighting and color. However, existing methods either do not distinguish different frequency bands or focus on only one band, which is insufficient under diverse lighting conditions. To perform comprehensive frequency domain learning, we propose a Multi-Frequency Expert Network (MFEN) that enables multi-frequency modulation and adaptively combines different bands through a mixture-of-experts design. We further introduce Random Frequency Augmentation (RFA) and Frequency Auxiliary Optimization (FAO) to better train MFEN. The three modules are complementary and jointly capture critical frequency-domain details for robust representation learning. Extensive experiments on three VI-ReID datasets demonstrate the effectiveness of our approach.

Related papers

• MTSIC: Multi-stage Transformer-based GAN for Spectral Infrared Image Colorization [26.33768545616346]
  Existing colorization methods rely on single-band images with limited spectral information and insufficient feature extraction capabilities.<n>In this paper, we propose a generative adversarial network (GAN)-based framework designed to integrate spectral information to enhance the colorization of infrared images.<n> Experimental results demonstrate that the proposed method significantly outperforms traditional techniques and effectively enhances the visual quality of infrared images.
  arXiv  Detail & Related papers  (2025-06-21T01:42:25Z)
• Freqformer: Image-Demoiréing Transformer via Efficient Frequency Decomposition [83.40450475728792]
  We present Freqformer, a Transformer-based framework specifically designed for image demoir'eing through targeted frequency separation.<n>Our method performs an effective frequency decomposition that explicitly splits moir'e patterns into high-frequency spatially-localized textures and low-frequency scale-robust color distortions.<n>Experiments on various demoir'eing benchmarks demonstrate that Freqformer achieves state-of-the-art performance with a compact model size.
  arXiv  Detail & Related papers  (2025-05-25T12:23:10Z)
• Frequency Enhancement for Image Demosaicking [40.76899837631637]
  We propose Dual-path Frequency Enhancement Network (DFENet), which reconstructs RGB images in a divide-and-conquer manner.<n>One path focuses on generating missing information through detail refinement in spatial domain, while the other aims at suppressing undesirable frequencies.<n>With these designs, the proposed DFENet outperforms other state-of-the-art algorithms on different datasets.
  arXiv  Detail & Related papers  (2025-03-20T02:37:10Z)
• Wavelet-Assisted Multi-Frequency Attention Network for Pansharpening [15.77836708727337]
  Pansharpening aims to combine a high-resolution panchromatic (PAN) image with a low-resolution multispectral (LRMS) image to produce a high-resolution multispectral (HRMS) image.<n>Although pansharpening in the frequency domain offers clear advantages, most existing methods either continue to operate solely in the spatial domain or fail to fully exploit the benefits of the frequency domain.<n>We propose Multi-Frequency Fusion Attention (MFFA), which leverages wavelet transforms to cleanly separate frequencies.
  arXiv  Detail & Related papers  (2025-02-07T13:15:49Z)
• FD2-Net: Frequency-Driven Feature Decomposition Network for Infrared-Visible Object Detection [16.80713499383237]
  Infrared-visible object detection (IVOD) seeks to harness the complementary information in infrared and visible images.<n>Existing methods often neglect the frequency characteristics of complementary information.<n>We introduce a novel Frequency-Driven Feature Decomposition Network for IVOD, called FD2-Net.
  arXiv  Detail & Related papers  (2024-12-12T13:19:05Z)
• Contourlet Refinement Gate Framework for Thermal Spectrum Distribution Regularized Infrared Image Super-Resolution [54.293362972473595]
  Image super-resolution (SR) aims to reconstruct high-resolution (HR) images from their low-resolution (LR) counterparts. Current approaches to address SR tasks are either dedicated to extracting RGB image features or assuming similar degradation patterns. We propose a Contourlet refinement gate framework to restore infrared modal-specific features while preserving spectral distribution fidelity.
  arXiv  Detail & Related papers  (2024-11-19T14:24:03Z)
• Frequency Domain Nuances Mining for Visible-Infrared Person Re-identification [75.87443138635432]
  Existing methods mainly exploit the spatial information while ignoring the discriminative frequency information. We propose a novel Frequency Domain Nuances Mining (FDNM) method to explore the cross-modality frequency domain information. Our method outperforms the second-best method by 5.2% in Rank-1 accuracy and 5.8% in mAP on the SYSU-MM01 dataset.
  arXiv  Detail & Related papers  (2024-01-04T09:19:54Z)
• 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)
• DEFormer: DCT-driven Enhancement Transformer for Low-light Image and Dark Vision [12.150160523389957]
  We propose a DCT-driven enhancement transformer (DEFormer) framework to restore lost details in the dark area.<n>Our framework has achieved superior results on the LOL and MIT-Adobe FiveK datasets.
  arXiv  Detail & Related papers  (2023-09-13T13:24:27Z)
• Flare-Aware Cross-modal Enhancement Network for Multi-spectral Vehicle Re-identification [29.48387524901101]
  In harsh environments, the discnative cues in RGB and NIR modalities are often lost due to strong flares from vehicle lamps or sunlight. We propose a Flare-Aware Cross-modal Enhancement Network that adaptively restores flare-corrupted RGB and NIR features with guidance from the flareimmunized thermal infrared spectrum.
  arXiv  Detail & Related papers  (2023-05-23T04:04:24Z)
• Adaptive Frequency Learning in Two-branch Face Forgery Detection [66.91715092251258]
  We propose Adaptively learn Frequency information in the two-branch Detection framework, dubbed AFD. We liberate our network from the fixed frequency transforms, and achieve better performance with our data- and task-dependent transform layers.
  arXiv  Detail & Related papers  (2022-03-27T14:25:52Z)

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.