# Inductive Unsupervised Domain Adaptation for Few-Shot Classification via Clustering

arXiv: https://arxiv.org/abs/2006.12816 · HTML: https://mlsanity.com/paper/2006.12816/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Jun 2020.

## Built on by (most cited first, 8 of 8)

- [Entity Concept-enhanced Few-shot Relation Extraction](https://mlsanity.com/paper/2106.02401/) (2021)
- [Dual-Gated Fusion with Prefix-Tuning for Multi-Modal Relation Extraction](https://mlsanity.com/paper/2306.11020/) (2023)
- [Event Causality Extraction with Event Argument Correlations](https://mlsanity.com/paper/2301.11621/) (2023)
- [Exploring Few-Shot Adaptation for Activity Recognition on Diverse Domains](https://mlsanity.com/paper/2305.08420/) (2023)
- [Cross Domain Few-Shot Learning via Meta Adversarial Training](https://mlsanity.com/paper/2202.05713/) (2022)
- [Few-Shot Domain Adaptation for Learned Image Compression](https://mlsanity.com/paper/2409.11111/) (2024)
- [RAPS: A Novel Few-Shot Relation Extraction Pipeline with Query-Information Guided Attention and Adaptive Prototype Fusion](https://mlsanity.com/paper/2210.08242/) (2022)
- [Cross-Domain Few-Shot Relation Extraction via Representation Learning and Domain Adaptation](https://mlsanity.com/paper/2212.02560/) (2022)

## Abstract (arXiv)

Few-shot classification tends to struggle when it needs to adapt to diverse domains. Due to the non-overlapping label space between domains, the performance of conventional domain adaptation is limited. Previous work tackles the problem in a transductive manner, by assuming access to the full set of test data, which is too restrictive for many real-world applications. In this paper, we set out to tackle this issue by introducing a inductive framework, DaFeC, to improve Domain adaptation performance for Few-shot classification via Clustering. We first build a representation extractor to derive features for unlabeled data from the target domain (no test data is necessary) and then group them with a cluster miner. The generated pseudo-labeled data and the labeled source-domain data are used as supervision to update the parameters of the few-shot classifier. In order to derive high-quality pseudo labels, we propose a Clustering Promotion Mechanism, to learn better features for the target domain via Similarity Entropy Minimization and Adversarial Distribution Alignment, which are combined with a Cosine Annealing Strategy. Experiments are performed on the FewRel 2.0 dataset. Our approach outperforms previous work with absolute gains (in classification accuracy) of 4.95%, 9.55%, 3.99% and 11.62%, respectively, under four few-shot settings.