SegQuant: A Semantics-Aware and Generalizable Quantization Framework for Diffusion Models
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917343168299008 |
|---|---|
| author | Zhang, Jiaji Sun, Ruichao Zhao, Hailiang Wu, Jiaju Chen, Peng Li, Hao Liu, Yuying Chow, Kingsum Xiong, Gang Deng, Shuiguang |
| author_facet | Zhang, Jiaji Sun, Ruichao Zhao, Hailiang Wu, Jiaju Chen, Peng Li, Hao Liu, Yuying Chow, Kingsum Xiong, Gang Deng, Shuiguang |
| contents | Diffusion models have demonstrated exceptional generative capabilities but are computationally intensive, posing significant challenges for deployment in resource-constrained or latency-sensitive environments. Quantization offers an effective means to reduce model size and computational cost, with post-training quantization (PTQ) being particularly appealing due to its compatibility with pre-trained models without requiring retraining or training data. However, existing PTQ methods for diffusion models often rely on architecture-specific heuristics that limit their generalizability and hinder integration with industrial deployment pipelines. To address these limitations, we propose SegQuant, a unified quantization framework that adaptively combines complementary techniques to enhance cross-model versatility. SegQuant consists of a segment-aware, graph-based quantization strategy (SegLinear) that captures structural semantics and spatial heterogeneity, along with a dual-scale quantization scheme (DualScale) that preserves polarity-asymmetric activations, which is crucial for maintaining visual fidelity in generated outputs. SegQuant is broadly applicable beyond Transformer-based diffusion models, achieving strong performance while ensuring seamless compatibility with mainstream deployment tools. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_14811 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SegQuant: A Semantics-Aware and Generalizable Quantization Framework for Diffusion Models Zhang, Jiaji Sun, Ruichao Zhao, Hailiang Wu, Jiaju Chen, Peng Li, Hao Liu, Yuying Chow, Kingsum Xiong, Gang Deng, Shuiguang Computer Vision and Pattern Recognition Artificial Intelligence Diffusion models have demonstrated exceptional generative capabilities but are computationally intensive, posing significant challenges for deployment in resource-constrained or latency-sensitive environments. Quantization offers an effective means to reduce model size and computational cost, with post-training quantization (PTQ) being particularly appealing due to its compatibility with pre-trained models without requiring retraining or training data. However, existing PTQ methods for diffusion models often rely on architecture-specific heuristics that limit their generalizability and hinder integration with industrial deployment pipelines. To address these limitations, we propose SegQuant, a unified quantization framework that adaptively combines complementary techniques to enhance cross-model versatility. SegQuant consists of a segment-aware, graph-based quantization strategy (SegLinear) that captures structural semantics and spatial heterogeneity, along with a dual-scale quantization scheme (DualScale) that preserves polarity-asymmetric activations, which is crucial for maintaining visual fidelity in generated outputs. SegQuant is broadly applicable beyond Transformer-based diffusion models, achieving strong performance while ensuring seamless compatibility with mainstream deployment tools. |
| title | SegQuant: A Semantics-Aware and Generalizable Quantization Framework for Diffusion Models |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2507.14811 |