Convolutional Neural Networks
MultiGrain
Introduced by Berman et al. in MultiGrain: a unified image embedding for classes and instancesMultiGrain is a type of image model that learns a single embedding for classes, instances and copies. In other words, it is a convolutional neural network that is suitable for both image classification and instance retrieval. We learn MultiGrain by jointly training an image embedding for multiple tasks. The resulting representation is compact and can outperform narrowly-trained embeddings. The learned embedding output incorporates different levels of granularity.
Source: MultiGrain: a unified image embedding for classes and instances
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Classification | 1 | 20.00% |
| General Classification | 1 | 20.00% |
| Image Classification | 1 | 20.00% |
| Image Retrieval | 1 | 20.00% |
| Retrieval | 1 | 20.00% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
Generalized Mean Pooling
|
Pooling Operations | |
PCA Whitening
|
Whitening | |
ResNet
|
Convolutional Neural Networks |
