Neural Architecture Search
Capsule Network
Introduced by Sabour et al. in Dynamic Routing Between CapsulesA capsule is an activation vector that basically executes on its inputs some complex internal computations. Length of these activation vectors signifies the probability of availability of a feature. Furthermore, the condition of the recognized element is encoded as the direction in which the vector is pointing. In traditional, CNN uses Max pooling for invariance activities of neurons, which is nothing except a minor change in input and the neurons of output signal will remains same.
Source: Dynamic Routing Between CapsulesPapers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Image Classification | 23 | 10.22% |
| General Classification | 20 | 8.89% |
| Classification | 18 | 8.00% |
| Sentiment Analysis | 10 | 4.44% |
| Semantic Segmentation | 6 | 2.67% |
| Text Classification | 6 | 2.67% |
| Image Segmentation | 5 | 2.22% |
| Medical Image Segmentation | 4 | 1.78% |
| Specificity | 4 | 1.78% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
