Turn Your ConvNet into a Zero-Shot Learner
Turn Your ConvNet into a Zero-Shot Learner
Classifier Crafting: Turn Your ConvNet into a Zero-Shot Learner!
DeepAI https://deepai.org/publication/classifier-crafting-turn-your-convnet-into-a-zero-shot-learner
arXiv paper abatract https://arxiv.org/abs/2103.11112
arXiv PDF paper https://arxiv.org/pdf/2103.11112v1.pdf
A Zero-shot learning (ZSL), classifies unseen categories. Their conclusion says:
Our papers shows that we can turn a convnet into a zeroshot learner by crafting the weights of the softmax operator, using fixed semantic/visual classification rules. We show that this strategy, when combined with an ensemble, and furthermore boosted by a predictions’ rebalancing, outperforms prior art in inductive zero-shot learning, on standard and generalized evaluation protocols, respectively. Since using a convnet for ZSL inference, we can achieve an interpretable predictor, at no additional cost, through neural attention by using methods such as GRAD-CAM as they are.
Stay up to date. Subscribe to my posts https://morrislee1234.wixsite.com/website/contact
Web site with my other posts by category https://morrislee1234.wixsite.com/website
LinkedIn https://www.linkedin.com/in/morris-lee-47877b7b
