HIGHLIGHTS
- who: Yassir Bendou and colleagues from the (UNIVERSITY) have published the paper: Easy—Ensemble Augmented-Shot-Y-Shaped Learning: State-of-the-Art Few-Shot Classification with Simple Components, in the Journal: (JOURNAL)
- what: The authors propose a way to train such models with aim reaching top performance on multiple standardized benchmarks in field. The authors propose to generate augmented feature vectors for each sample from the novel dataset. To boost performance even further, the authors propose to concatenate the feature vectors obtained from multiple backbones trained using the previously described method, but with different . . .
If you want to have access to all the content you need to log in!
Thanks :)
If you don't have an account, you can create one here.