UniTriGen: Unified Triplet Generation of Aligned Visible-Infrared-Label for Few-Shot RGB-T Semantic Segmentation
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911685561810944 |
|---|---|
| author | Zhou, Ping Wang, Haoyu Zheng, Mengmeng Zhang, Lei Wei, Wei Ding, Chen Zhou, Fei |
| author_facet | Zhou, Ping Wang, Haoyu Zheng, Mengmeng Zhang, Lei Wei, Wei Ding, Chen Zhou, Fei |
| contents | RGB-T semantic segmentation requires strictly aligned VIS-IR-Label triplets; however, such aligned triplet data are often scarce in real-world scenarios. Existing generative augmentation methods usually adopt cascaded generation paradigms, decomposing joint triplet generation into local conditional processes. As a result, consistency among VIS, IR, and Label in spatial structure, semantic content, and cross-modal details cannot be reliably maintained. To address this issue, we propose UniTriGen, a unified triplet generation framework that directly generates spatially aligned, semantically consistent, and modality complementary VIS-IR-Label triplets under the guidance of text prompts. UniTriGen first introduces a unified triplet generation mechanism, where VIS, IR, and Label are jointly encoded into a shared latent space and modeled with a diffusion process to enforce global cross-modal consistency. Lightweight modality-specific residual adapters are further integrated into this mechanism to accommodate modality-specific imaging characteristics and output formats. To mitigate generation bias caused by imbalanced scene and class distributions in limited paired triplets, UniTriGen also employs a scene-balanced and class-aware few-shot sampling strategy, which induces a more balanced sampling distribution and enhances the scene and class diversity of generated triplets. Experiments show that UniTriGen generates high-quality aligned triplets from limited real paired data, thereby achieving consistent performance improvements across various RGB-T semantic segmentation models. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_14626 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | UniTriGen: Unified Triplet Generation of Aligned Visible-Infrared-Label for Few-Shot RGB-T Semantic Segmentation Zhou, Ping Wang, Haoyu Zheng, Mengmeng Zhang, Lei Wei, Wei Ding, Chen Zhou, Fei Computer Vision and Pattern Recognition RGB-T semantic segmentation requires strictly aligned VIS-IR-Label triplets; however, such aligned triplet data are often scarce in real-world scenarios. Existing generative augmentation methods usually adopt cascaded generation paradigms, decomposing joint triplet generation into local conditional processes. As a result, consistency among VIS, IR, and Label in spatial structure, semantic content, and cross-modal details cannot be reliably maintained. To address this issue, we propose UniTriGen, a unified triplet generation framework that directly generates spatially aligned, semantically consistent, and modality complementary VIS-IR-Label triplets under the guidance of text prompts. UniTriGen first introduces a unified triplet generation mechanism, where VIS, IR, and Label are jointly encoded into a shared latent space and modeled with a diffusion process to enforce global cross-modal consistency. Lightweight modality-specific residual adapters are further integrated into this mechanism to accommodate modality-specific imaging characteristics and output formats. To mitigate generation bias caused by imbalanced scene and class distributions in limited paired triplets, UniTriGen also employs a scene-balanced and class-aware few-shot sampling strategy, which induces a more balanced sampling distribution and enhances the scene and class diversity of generated triplets. Experiments show that UniTriGen generates high-quality aligned triplets from limited real paired data, thereby achieving consistent performance improvements across various RGB-T semantic segmentation models. |
| title | UniTriGen: Unified Triplet Generation of Aligned Visible-Infrared-Label for Few-Shot RGB-T Semantic Segmentation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2605.14626 |