Discovering Latent Domains for Multisource Domain Adaptation

By Judy Hoffman, Brian Kulis, Trevor Darrell, Kate Saenko. 2012

199 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Cancer Research, Computer Vision and Pattern Recognition, 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 Cancer Research

In Computer Vision and Pattern Recognition

In Representation & Self-Supervised Learning

Citations in the corpus

Multiple-Source Adaptation with Domain Classifiers (2020, methodology): “The rest of the proof follows from Hoffman et al. [2018]: The unnormalized relative entropy B(· ‖ ·) is jointly convex, thus B(Kz ‖ Jz) is convex; (Kz − Jz) is an affine function of z and is therefore convex too.”
Agnostic Federated Learning (2019, background): “…more closely related to that of federated learning is that of multiple-source adaptation , ﬁrst formalized and analyzed theoretically by Mansour, Mohri, and Rostamizadeh (2009c,a) and later studied for various applications such as object recognition (Hoffman et al., 2012; Gong et al., 2013a,b).”
Algorithms and Theory for Multiple-Source Adaptation (2018, background): “Khosla et al. (2012) considered a similar setting where the learner trains a single predictor for any target domain and where the learner has access to source data but not target data. However, Khosla et al. (2012) combine all the source data to jointly train the final predictor and a large set of c”
Conditional variance penalties and domain shift robustness (2017, background): “This also differentiates this work from latent domain adaptation papers from the computer vision literature (Hoffman et al., 2012; Gong et al., 2013).”
Deep Domain Confusion: Maximizing for Domain Invariance (2014, background): “In the last few years several methods for visual domain adaptation have been suggested to overcome this issue [10, 33, 2, 29, 25, 22, 17, 16, 19, 20], but were limited to shallow models.”
Learning Multi-domain Convolutional Neural Networks for Visual Tracking (2015, methodology): “[19] presented a mixture-transform model for object classiﬁcation.”
One-Shot Adaptation of Supervised Deep Convolutional Models (2013, methodology): “Many visual domain adaptation methods have been put forth to compensate for dataset bias [7, 22, 1, 20, 18, 16, 13, 12, 14, 15], but are limited to shallow models.”
Domain Adaptation for Visual Applications: A Comprehensive Survey (2017, methodology): “Furthermore, in the case of multi-source domain adaptation [143, 67, 227, 265, 220, 116, 200, 102, 107, 52] different source speciﬁc tasks are jointly exploited in the interest of the target task.”
A Deeper Look at Dataset Bias (2015, methodology): “Several domain adaptive methods have been tested on setups extracted from multiple datasets [12,16] and some approaches proposed to identify the latent domains in the data collections before applying domain adaptation solutions [22,14,43].”
Distributionally Robust Language Modeling (2019, background): “For instance, Hoffman et al. (2012) and Xiong et al. (2014) discover latent domains in classiﬁcation by clustering data using class labels.”
Med3D: Transfer Learning for 3D Medical Image Analysis (2019, methodology): “Hoffman et al. [27] introduced a mixture-transform model for object classiﬁcation and Nam et al. [28] presented a domain adaptation network for video tracking.”
Open Compound Domain Adaptation (2019, background): “The goal is to extend unsupervised domain adaptation to latent [16, 51, 32] or multiple [11, 9, 54] or continuous [2, 13, 31, 50] target domains, when only the source domain has class labels.”
Test-Time Training with Self-Supervision for Generalization under Distribution Shifts (2019, background): “Prior work try to anticipate broader distributions by using multiple and evolving domains (Hoffman et al., 2018; 2012; 2014).”
Unsupervised Domain Adaptation via Structurally Regularized Deep Clustering (2020, background): “Methods of latent domain discovery [10, 18, 22, 39] focus on capturing latent structures of the source, target data or a mixed one under the assumption that data may practically comprise multiple diverse distributions.”
Discovering Attribute Shades of Meaning with the Crowd (2015, methodology): “Other approaches find within-category modes in order to perform better domain adaptation for object recognition (Hoffman et al, 2012; Gong et al, 2013; Xiong et al, 2014).”
I Have Seen Enough: Transferring Parts Across Categories (2016, background): “Sometimes, the source domains are not given a priori, but discovered implicitly [20].”
Domain adaptive sparse representation-based classification (2015, unknown): “76 LMSDA [30] 82.”
Towards Knowledgeable Supervised Lifelong Learning Systems (2020, unknown): “, 2012) (Hoffman et al., 2012) (Bengio, 2012) (Oquab, Bottou, Laptev, & Sivic, 2014) (Yosinski et al.”