paper-with-me

홈 › Papers

Unsupervised Embedding Adaptation via Early-Stage Feature Reconstruction for Few-Shot Classification

2021-06-22 · Dong Hoon Lee, Sae-Young Chung

We propose unsupervised embedding adaptation for the downstream few-shot classification task. Based on findings that deep neural networks learn to generalize before memorizing, we develop Early-Stage Feature Reconstruction (ESFR) -- a novel adaptation scheme with feature reconstruction and dimensionality-driven early stopping that finds generalizable features. Incorporating ESFR consistently improves the performance of baseline methods on all standard settings, including the recently proposed transductive method. ESFR used in conjunction with the transductive method further achieves state-of-the-art performance on mini-ImageNet, tiered-ImageNet, and CUB; especially with 1.2%~2.0% improvements in accuracy over the previous best performing method on 1-shot setting.

📄 PDF Abstract BibTeX arXiv:2106.11486

Code (1)

movinghoon/ESFR 공식 구현 tf

Tasks

Few-Shot Image ClassificationFew-Shot Learning

Methods 이 논문이 사용한 방법론

Early Stopping Early Stopping is a regularization technique for deep neural networks that stops training when parameter updates no longer begin to yield improves on a validation set. In…

Similar Papers 제목 키워드 기반

Part-of-Speech Tagging for Historical English

2016-03-10 · NAACL 2016 6 · Yi Yang, Jacob Eisenstein

As more historical texts are digitized, there is interest in applying natural language processing tools to these archives. However, the performance of these tools is often unsatisfactory, due to language change and genre…

Domain AdaptationPart-Of-Speech TaggingUnsupervised Domain AdaptationWord Embeddings

Unsupervised Domain Adaptation with Feature Embeddings

2014-12-14 · Yi Yang, Jacob Eisenstein

Representation learning is the dominant technique for unsupervised domain adaptation, but existing approaches often require the specification of "pivot features" that generalize across domains, which are selected by task…

Domain AdaptationRepresentation LearningUnsupervised Domain Adaptation

Pseudo-Labeling Curriculum for Unsupervised Domain Adaptation

2019-08-01 · Jaehoon Choi, Minki Jeong, Taekyung Kim, Changick Kim

To learn target discriminative representations, using pseudo-labels is a simple yet effective approach for unsupervised domain adaptation. However, the existence of false pseudo-labels, which may have a detrimental influ…

ClusteringDomain AdaptationSemi-Supervised Image ClassificationUnsupervised Domain Adaptation

Self-supervised Feature Adaptation for 3D Industrial Anomaly Detection

2024-01-06 · Yuanpeng Tu, Boshen Zhang, Liang Liu, Yuxi Li 외

Industrial anomaly detection is generally addressed as an unsupervised task that aims at locating defects with only normal training samples. Recently, numerous 2D anomaly detection methods have been proposed and have ach…

Anomaly Detectioncross-modal alignment

Prototypical Cross-domain Self-supervised Learning for Few-shot Unsupervised Domain Adaptation

2021-03-31 · CVPR 2021 1 · Xiangyu Yue, Zangwei Zheng, Shanghang Zhang, Yang Gao 외

Unsupervised Domain Adaptation (UDA) transfers predictive models from a fully-labeled source domain to an unlabeled target domain. In some applications, however, it is expensive even to collect labels in the source domai…

Contrastive LearningDomain AdaptationSelf-Supervised LearningSemantic Segmentation+1