Task-Adaptive Pseudo Labeling for Transductive Meta-Learning

2023-04-21 · Sanghyuk Lee, SeungHyun Lee, Byung Cheol Song

Meta-learning performs adaptation through a limited amount of support set, which may cause a sample bias problem. To solve this problem, transductive meta-learning is getting more and more attention, going beyond the conventional inductive learning perspective. This paper proposes so-called task-adaptive pseudo labeling for transductive meta-learning. Specifically, pseudo labels for unlabeled query sets are generated from labeled support sets through label propagation. Pseudo labels enable to adopt the supervised setting as it is and also use the unlabeled query set in the adaptation process. As a result, the proposed method is able to deal with more examples in the adaptation process than inductive ones, which can result in better classification performance of the model. Note that the proposed method is the first approach of applying task adaptation to pseudo labeling. Experiments show that the proposed method outperforms the state-of-the-art (SOTA) technique in 5-way 1-shot few-shot classification.

📄 PDF Abstract BibTeX arXiv:2304.11173

Code (0)

등록된 구현이 없습니다.

Tasks

Inductive LearningMeta-Learning

Generating Pseudo-labels Adaptively for Few-shot Model-Agnostic Meta-Learning

2022-07-09 · Guodong Liu, Tongling Wang, Shuoxi Zhang, Kun He

Model-Agnostic Meta-Learning (MAML) is a famous few-shot learning method that has inspired many follow-up efforts, such as ANIL and BOIL. However, as an inductive method, MAML is unable to fully utilize the information o…

Few-Shot Learning Meta-Learning Pseudo Label

Enhancing CLIP with CLIP: Exploring Pseudolabeling for Limited-Label Prompt Tuning

2023-06-02 · NeurIPS 2023 11 · Cristina Menghini, Andrew Delworth, Stephen H. Bach

Fine-tuning vision-language models (VLMs) like CLIP to downstream tasks is often necessary to optimize their performance. However, a major obstacle is the limited availability of labeled data. We study the use of pseudol…

image-classification Image Classification Zero-Shot Learning

Multi-class Probabilistic Bounds for Self-learning

2021-09-29 · Vasilii Feofanov, Emilie Devijver, Massih-Reza Amini

Self-learning is a classical approach for learning with both labeled and unlabeled observations which consists in giving pseudo-labels to unlabeled training instances with a confidence score over a predetermined threshol…

Multi-class Classification Self-Learning

Adaptive Self-training for Neural Sequence Labeling with Few Labels

2021-01-01 · Yaqing Wang, Subhabrata Mukherjee, Haoda Chu, Yuancheng Tu 외

Neural sequence labeling is an important technique employed for many Natural Language Processing (NLP) tasks, such as Named Entity Recognition (NER), slot tagging for dialog systems and semantic parsing. Large-scale pre-…

Meta-Learning named-entity-recognition Named Entity Recognition Named Entity Recognition (NER)+2

Meta-Learned Confidence for Transductive Few-shot Learning

2021-01-01 · Seong Min Kye, Hae Beom Lee, Hoirin Kim, Sung Ju Hwang

Transductive inference is an effective means of tackling the data deficiency problem in few-shot learning settings. A popular transductive inference technique for few-shot metric-based approaches, is to update the protot…

Few-Shot Learning Meta-Learning