Latent Embedding Feedback and Discriminative Features for Zero-Shot Classification

By Sanath Narayan, Akshita Gupta, Fahad Shahbaz Khan, Cees G. M. Snoek, Ling Shao. 2020

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Ali Cheraghian
2. Shafin Rahman
3. Lars Petersson
4. Mehrtash Harandi
5. Pengfei Fang
6. Soumava Kumar Roy
7. Ping Wang
8. Kun Yan

Citations in the corpus

• Semantic-aware Knowledge Distillation for Few-Shot Class-Incremental Learning (2021, background): “Being inspired by the literature on zero-shot learning [7, 6, 5, 20, 37, 24, 25], given an image as input, we estimate the semantic word vectors for the input instead of directly predicting its class label.”
• Adaptive and Generative Zero-Shot Learning (2021, background): “The ZSL performance improves 4.6 % on AWA2 , 2.4 % on CUB , 1.7 % on SUN , and 2.8 % on aPY , respectively.”
• Aligning Visual Prototypes with BERT Embeddings for Few-Shot Learning (2021, methodology): “Within a wider scope, textual features have also been used for zero-shot image classification [3, 8, 29, 57].”