All you need is a good representation: A multi-level and classifier-centric representation for few-shot learning

By Shaoli Huang, Dacheng Tao. 2019

16 citations recorded by the source corpus.

Subfields: Representation & Self-Supervised Learning

How researchers see this paper

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

In Representation & Self-Supervised Learning

1. Dapeng Chen
2. Yixiao Ge
3. Wanli Ouyang
4. Lei Bai
5. Shixiang Tang

Citations in the corpus

• Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need? (2020, neutral): “The findings in concurrent works [6, 20] are inline with our simple baseline.”
• Revisiting Mid-Level Patterns for Cross-Domain Few-Shot Recognition (2020, unknown): “The only work makes use of mid-level features, to the best of our knowledge, is [18], which directly applied mid-level features to the classification.”
• Mutual CRF-GNN for Few-shot Learning (2021, background): “Feature pretrained few-shot learning is implemented by [50, 42, 22], where the feature embedding is trained by all samples in the meta-training stage.”