IPNET:Influential Prototypical Networks for Few Shot Learning
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2022
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866929418993139712 |
|---|---|
| author | Chowdhury, Ranjana Roy Bathula, Deepti R. |
| author_facet | Chowdhury, Ranjana Roy Bathula, Deepti R. |
| contents | Prototypical network (PN) is a simple yet effective few shot learning strategy. It is a metric-based meta-learning technique where classification is performed by computing Euclidean distances to prototypical representations of each class. Conventional PN attributes equal importance to all samples and generates prototypes by simply averaging the support sample embeddings belonging to each class. In this work, we propose a novel version of PN that attributes weights to support samples corresponding to their influence on the support sample distribution. Influence weights of samples are calculated based on maximum mean discrepancy (MMD) between the mean embeddings of sample distributions including and excluding the sample. Further, the influence factor of a sample is measured using MMD based on the shift in the distribution in the absence of that sample. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2208_09345 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | IPNET:Influential Prototypical Networks for Few Shot Learning Chowdhury, Ranjana Roy Bathula, Deepti R. Computer Vision and Pattern Recognition Prototypical network (PN) is a simple yet effective few shot learning strategy. It is a metric-based meta-learning technique where classification is performed by computing Euclidean distances to prototypical representations of each class. Conventional PN attributes equal importance to all samples and generates prototypes by simply averaging the support sample embeddings belonging to each class. In this work, we propose a novel version of PN that attributes weights to support samples corresponding to their influence on the support sample distribution. Influence weights of samples are calculated based on maximum mean discrepancy (MMD) between the mean embeddings of sample distributions including and excluding the sample. Further, the influence factor of a sample is measured using MMD based on the shift in the distribution in the absence of that sample. |
| title | IPNET:Influential Prototypical Networks for Few Shot Learning |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2208.09345 |