Neural Experts: Mixture of Experts for Implicit Neural Representations
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916457379528704 |
|---|---|
| author | Ben-Shabat, Yizhak Koneputugodage, Chamin Hewa Ramasinghe, Sameera Gould, Stephen |
| author_facet | Ben-Shabat, Yizhak Koneputugodage, Chamin Hewa Ramasinghe, Sameera Gould, Stephen |
| contents | Implicit neural representations (INRs) have proven effective in various tasks including image, shape, audio, and video reconstruction. These INRs typically learn the implicit field from sampled input points. This is often done using a single network for the entire domain, imposing many global constraints on a single function. In this paper, we propose a mixture of experts (MoE) implicit neural representation approach that enables learning local piece-wise continuous functions that simultaneously learns to subdivide the domain and fit locally. We show that incorporating a mixture of experts architecture into existing INR formulations provides a boost in speed, accuracy, and memory requirements. Additionally, we introduce novel conditioning and pretraining methods for the gating network that improves convergence to the desired solution. We evaluate the effectiveness of our approach on multiple reconstruction tasks, including surface reconstruction, image reconstruction, and audio signal reconstruction and show improved performance compared to non-MoE methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_21643 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Neural Experts: Mixture of Experts for Implicit Neural Representations Ben-Shabat, Yizhak Koneputugodage, Chamin Hewa Ramasinghe, Sameera Gould, Stephen Computer Vision and Pattern Recognition Implicit neural representations (INRs) have proven effective in various tasks including image, shape, audio, and video reconstruction. These INRs typically learn the implicit field from sampled input points. This is often done using a single network for the entire domain, imposing many global constraints on a single function. In this paper, we propose a mixture of experts (MoE) implicit neural representation approach that enables learning local piece-wise continuous functions that simultaneously learns to subdivide the domain and fit locally. We show that incorporating a mixture of experts architecture into existing INR formulations provides a boost in speed, accuracy, and memory requirements. Additionally, we introduce novel conditioning and pretraining methods for the gating network that improves convergence to the desired solution. We evaluate the effectiveness of our approach on multiple reconstruction tasks, including surface reconstruction, image reconstruction, and audio signal reconstruction and show improved performance compared to non-MoE methods. |
| title | Neural Experts: Mixture of Experts for Implicit Neural Representations |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2410.21643 |