VNE (BOIL)

Reported on 4 benchmarks across 2 tasks · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Computer Vision4 results

Image ClassificationonMini-Imagenet 5-way (5-shot)
Accuracy· 2023-04-04
67.52
best: 98.72 (SgVA-CLIP)
VNE: An Effective Method for Improving Deep Representation by Manipulating Eigenvalue Distribution arXiv:2304.01434
Image ClassificationonMini-Imagenet 5-way (1-shot)
Accuracy· 2023-04-04
50.95
best: 97.95 (SgVA-CLIP)
VNE: An Effective Method for Improving Deep Representation by Manipulating Eigenvalue Distribution arXiv:2304.01434
Few-Shot Image ClassificationonMini-Imagenet 5-way (5-shot)
Accuracy· 2023-04-04
67.52
best: 98.72 (SgVA-CLIP)
VNE: An Effective Method for Improving Deep Representation by Manipulating Eigenvalue Distribution arXiv:2304.01434
Few-Shot Image ClassificationonMini-Imagenet 5-way (1-shot)
Accuracy· 2023-04-04
50.95
best: 97.95 (SgVA-CLIP)
VNE: An Effective Method for Improving Deep Representation by Manipulating Eigenvalue Distribution arXiv:2304.01434