CrossTransformers is a Transformer-based neural network architecture which can take a small number of labeled images and an unlabeled query, find coarse spatial correspondence between the query and the labeled images, and then infer class membership by computing distances between spatially-corresponding features.
Source: CrossTransformers: spatially-aware few-shot transferPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Classification | 1 | 11.11% |
Few-Shot Learning | 1 | 11.11% |
Meta-Learning | 1 | 11.11% |
Object Recognition | 1 | 11.11% |
Pose Estimation | 1 | 11.11% |
Semantic Segmentation | 1 | 11.11% |
Action Recognition | 1 | 11.11% |
Few Shot Action Recognition | 1 | 11.11% |
Self-Supervised Learning | 1 | 11.11% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |