DSS-GAN：基于Mamba架构的定向状态空间GAN用于类条件图像合成
DSS-GAN: Directional State Space GAN with Mamba backbone for Class-Conditional Image Synthesis
AI总结：
DSS-GAN引入了定向潜在路由机制，通过分解潜在向量并结合类别嵌入，提升图像合成的FID、KID和精度召回率。
摘要：
我们提出了DSS-GAN，首个采用Mamba作为分层生成器主干网络的生成对抗网络，用于噪声到图像合成。核心贡献是定向潜在路由（DLR），一种新的条件机制，将潜在向量分解为方向特定的子向量，每个子向量与类别嵌入联合投影，生成对应的Mamba扫描的特征级仿射调制。与传统类别条件注入全局信号不同，DLR在特征图的distinct空间轴上耦合类别身份和潜在结构，应用于所有生成尺度。DSS-GAN在多个测试数据集上相比StyleGAN2-ADA取得了更高的FID、KID和精度召回率。对潜在空间的分析显示，方向子向量表现出可测量的专业化：沿单个组件的扰动会产生结构化的、方向相关的合成图像变化。
英文摘要：
We present DSS-GAN, the first generative adversarial network to employ Mamba as a hierarchical generator backbone for noise-to-image synthesis. The central contribution is Directional Latent Routing (DLR), a novel conditioning mechanism that decomposes the latent vector into direction-specific subvectors, each jointly projected with a class embedding to produce a feature-wise affine modulation of the corresponding Mamba scan. Unlike conventional class conditioning that injects a global signal, DLR couples class identity and latent structure along distinct spatial axes of the feature map, applied consistently across all generative scales. DSS-GAN achieves improved FID, KID, and precision-recall scores compared to StyleGAN2-ADA across multiple tested datasets. Analysis of the latent space reveals that directional subvectors exhibit measurable specialization: perturbations along individual components produce structured, direction-correlated changes in the synthesized image.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
