Coupled Inference in Diffusion Models for Semantic Decomposition
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915788649136128 |
|---|---|
| author | Yeung, Calvin Zakeri, Ali Zou, Zhuowen Imani, Mohsen |
| author_facet | Yeung, Calvin Zakeri, Ali Zou, Zhuowen Imani, Mohsen |
| contents | Many visual scenes can be described as compositions of latent factors. Effective recognition, reasoning, and editing often require not only forming such compositional representations, but also solving the decomposition problem. One popular choice for constructing these representations is through the binding operation. Resonator networks, which can be understood as coupled Hopfield networks, were proposed as a way to perform decomposition on such bound representations. Recent works have shown notable similarities between Hopfield networks and diffusion models. Motivated by these observations, we introduce a framework for semantic decomposition using coupled inference in diffusion models. Our method frames semantic decomposition as an inverse problem and couples the diffusion processes using a reconstruction-driven guidance term that encourages the composition of factor estimates to match the bound vector. We also introduce a novel iterative sampling scheme that improves the performance of our model. Finally, we show that attention-based resonator networks are a special case of our framework. Empirically, we demonstrate that our coupled inference framework outperforms resonator networks across a range of synthetic semantic decomposition tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_09983 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Coupled Inference in Diffusion Models for Semantic Decomposition Yeung, Calvin Zakeri, Ali Zou, Zhuowen Imani, Mohsen Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Many visual scenes can be described as compositions of latent factors. Effective recognition, reasoning, and editing often require not only forming such compositional representations, but also solving the decomposition problem. One popular choice for constructing these representations is through the binding operation. Resonator networks, which can be understood as coupled Hopfield networks, were proposed as a way to perform decomposition on such bound representations. Recent works have shown notable similarities between Hopfield networks and diffusion models. Motivated by these observations, we introduce a framework for semantic decomposition using coupled inference in diffusion models. Our method frames semantic decomposition as an inverse problem and couples the diffusion processes using a reconstruction-driven guidance term that encourages the composition of factor estimates to match the bound vector. We also introduce a novel iterative sampling scheme that improves the performance of our model. Finally, we show that attention-based resonator networks are a special case of our framework. Empirically, we demonstrate that our coupled inference framework outperforms resonator networks across a range of synthetic semantic decomposition tasks. |
| title | Coupled Inference in Diffusion Models for Semantic Decomposition |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2602.09983 |