Cargando…
Relieving the Incompatibility of Network Representation and Classification for Long-Tailed Data Distribution
In the real-world scenario, data often have a long-tailed distribution and training deep neural networks on such an imbalanced dataset has become a great challenge. The main problem caused by a long-tailed data distribution is that common classes will dominate the training results and achieve a very...
Autores principales: | , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Hindawi
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8723848/ https://www.ncbi.nlm.nih.gov/pubmed/34987568 http://dx.doi.org/10.1155/2021/6702625 |