Transfer Feature Learning with Joint Distribution Adaptation

By Mingsheng Long, Jianmin Wang, Guiguang Ding, Jiaguang Sun, Philip S. Yu. 2013

1,833 citations recorded by the source corpus.

Subfields: Artificial Intelligence, 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 Artificial Intelligence

In Representation & Self-Supervised Learning

Citations in the corpus

Coupled Generative Adversarial Networks (2016, methodology): “Method [17] [18] [19] [20] CoGAN From MNIST 0.”
Adversarial Discriminative Domain Adaptation (2017, methodology): “For adaptation between MNIST and USPS, we follow the training protocol established in [25], sampling 2000 images from MNIST and 1800 from USPS.”
Learning Transferable Features with Deep Adaptation Networks (2015, methodology): “A rich line of prior works have focused on learning shallow features by jointly minimizing a distance metric of domain discrepancy (Pan et al., 2011; Long et al., 2013; Baktashmotlagh et al., 2013; Gong et al., 2013; Zhang et al., 2013; Ghifary et al., 2014; Wang & Schneider, 2014).”
Self-Supervised Training Enhances Online Continual Learning (2021, methodology): “This set of experiments is similar to standard transfer learning and domain adaptation setups [42, 43, 52, 70], and could prove especially useful when performing continual learning on small datasets that require rich and generalizable feature representations.”
A Comprehensive Survey on Transfer Learning (2019, methodology): “Different from JDA which assumes that the marginal and the conditional distributions have the same importance in adaptation, BDA attempts to balance the marginal and the conditional distribution adaptation.”
Unlabeled Data Improves Adversarial Robustness (2019, neutral): “[27] M.”
Deep Hashing Network for Unsupervised Domain Adaptation (2017, methodology): “The standard datasets for vision based domain adaptation are, facial expression datasets CKPlus [35] and MMI [40], digit datasets SVHN [36], USPS and MNIST[28], head pose recognition datasets PIE [33], object recognition datasets COIL[33], Office [42] and Office-Caltech [20].”
Domain Adaptation for Visual Applications: A Comprehensive Survey (2017, background): “on [167, 275, 274], sentiment analysis [35, 100], WiFi-based localization [159], speech recognition across different speakers [132, 175], object recognition in images acquired in different conditions [185, 103, 83, 140, 216], video concept detection [259], video event recognition [69], activity reco”
Contrastive Adaptation Network for Unsupervised Domain Adaptation (2019, neutral): “[19] and Pei et al .”
No More Discrimination: Cross City Adaptation of Road Scene Segmenters (2017, background): “Under such unsupervised settings, we extend the idea in [20] and assign pseudo labels to pixels/grids in the images of the target domain.”
Generate to Adapt: Aligning Domains Using Generative Adversarial Networks (2017, methodology): “MN→US (p) denotes the MN→US experiment run using the protocol established in [17], while MN→US (f) denotes the experiment run using the entire datasets.”
Adaptation Across Extreme Variations using Unlabeled Domain Bridges (2019, methodology): “Recent works use kernel-based methods such as maximum mean discrepancy (MMD) [34, 52, 54, 35] and optimum transport (OT) [10, 11] to measure the domain difference in the feature level space.”
Adversarial Domain Adaptation With Prototype-Based Normalized Output Conditioner (2020, background): “[29], [40] show that pseudo-labels can help mitigate the joint distribution discrepancy via minimizing multiple class-wise MMD measures.”
Understanding Self-Training for Gradual Domain Adaptation (2020, background): “, 2020) and domain adaptation (Long et al., 2013; Zou et al., 2019; Inoue et al., 2018), and is related to entropy minimization (Grandvalet and Bengio, 2005).”
Applications of Unsupervised Deep Transfer Learning to Intelligent Fault Diagnosis: A Survey and Comparative Study (2019, background): “Wu et al. [104] further used the grey wolf optimization algorithm to learn the parameters of JDA.”
Transfer Learning for EEG-Based Brain–Computer Interfaces: A Review of Progress Made Since 2016 (2020, positive): “In this way, it achieved joint distribution adaptation [100].”