Label Efficient Learning of Transferable Representations across Domains and Tasks

2017-11-30 · NeurIPS 2017 · Zelun Luo, Yuliang Zou, Judy Hoffman, Li Fei-Fei

We propose a framework that learns a representation transferable across different domains and tasks in a label efficient manner. Our approach battles domain shift with a domain adversarial loss, and generalizes the embedding to novel task using a metric learning-based approach. Our model is simultaneously optimized on labeled source data and unlabeled or sparsely labeled data in the target domain. Our method shows compelling results on novel classes within a new domain even when only a few labeled examples per class are available, outperforming the prevalent fine-tuning approach. In addition, we demonstrate the effectiveness of our framework on the transfer learning task from image object recognition to video action recognition.

📄 PDF Abstract BibTeX arXiv:1712.00123

Code (0)

등록된 구현이 없습니다.

Tasks

Action Recognition Metric Learning Object Recognition Temporal Action Localization Transfer Learning

Label Efficient Learning of Transferable Representations acrosss Domains and Tasks

2017-12-01 · NeurIPS 2017 12 · Zelun Luo, Yuliang Zou, Judy Hoffman, Li F. Fei-Fei

We propose a framework that learns a representation transferable across different domains and tasks in a data efficient manner. Our approach battles domain shift with a domain adversarial loss, and generalizes the embedd…

Action Recognition Metric Learning Object Recognition Temporal Action Localization+1

Learning Task-oriented Disentangled Representations for Unsupervised Domain Adaptation

2020-07-27 · Pingyang Dai, Peixian Chen, Qiong Wu, Xiaopeng Hong 외

Unsupervised domain adaptation (UDA) aims to address the domain-shift problem between a labeled source domain and an unlabeled target domain. Many efforts have been made to address the mismatch between the distributions …

Domain Adaptation Retrieval Unsupervised Domain Adaptation

Deep causal representation learning for unsupervised domain adaptation

2019-10-28 · Raha Moraffah, Kai Shu, Adrienne Raglin, Huan Liu

Studies show that the representations learned by deep neural networks can be transferred to similar prediction tasks in other domains for which we do not have enough labeled data. However, as we transition to higher laye…

Domain Adaptation Representation Learning Unsupervised Domain Adaptation

Learning Transferable Adversarial Robust Representations via Multi-view Consistency

2022-10-19 · Minseon Kim, Hyeonjeong Ha, Dong Bok Lee, Sung Ju Hwang

Despite the success on few-shot learning problems, most meta-learned models only focus on achieving good performance on clean examples and thus easily break down when given adversarially perturbed samples. While some rec…

Adversarial Attack Adversarial Robustness Domain Adaptation Few-Shot Learning+3

Noise May Contain Transferable Knowledge: Understanding Semi-supervised Heterogeneous Domain Adaptation from an Empirical Perspective

2025-02-19 · Yuan YAO, Xiaopu Zhang, Yu Zhang, Jian Jin 외

Semi-supervised heterogeneous domain adaptation (SHDA) addresses learning across domains with distinct feature representations and distributions, where source samples are labeled while most target samples are unlabeled, …

Domain Adaptation Transfer Learning