Backbone Architectures
Spatial Broadcast Decoder
Introduced by Watters et al. in Spatial Broadcast Decoder: A Simple Architecture for Learning Disentangled Representations in VAEsSpatial Broadcast Decoder is an architecture that aims to improve disentangling, reconstruction accuracy, and generalization to held-out regions in data space. It provides a particularly dramatic benefit when applied to datasets with small objects.
Source: Watters et al.
Image source: Watters et al.
Source: Spatial Broadcast Decoder: A Simple Architecture for Learning Disentangled Representations in VAEs
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| BIG-bench Machine Learning | 2 | 6.25% |
| Semantic Segmentation | 2 | 6.25% |
| Object Discovery | 2 | 6.25% |
| Unsupervised Object Segmentation | 2 | 6.25% |
| blind source separation | 1 | 3.13% |
| Speech Separation | 1 | 3.13% |
| Clustering | 1 | 3.13% |
| Superpixels | 1 | 3.13% |
| Interactive Segmentation | 1 | 3.13% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
