Geodesic flow kernel for unsupervised domain adaptation

By Boqing Gong, Yuan Shi, Fei Sha, Kristen Grauman. 2012

2,444 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

Semi-Supervised QA with Generative Domain-Adaptive Nets (2017, methodology): “There are also methods seeking a domain transition from the source domain to the target domain (Gong et al., 2012; Gopalan et al., 2011; Pan et al., 2011).”
Meta-learning with differentiable closed-form solvers (2018, neutral): “For instance, the popular Ofﬁce-Caltech (Gong et al., 2012) dataset is constructed by considering all the images from 10 classes present in 4 different datasets (the domains).”
Domain-Adversarial Training of Neural Networks (2015, methodology): “Note also that several approaches perform transition from the source to the target domain (Gopalan et al., 2011; Gong et al., 2012) by changing gradually the training distribution.”
Learning Transferable Features with Deep Adaptation Networks (2015, methodology): “Ofﬁce-10 + Caltech-10 (Gong et al., 2012) This dataset consists of the 10 common categories shared by the Ofﬁce-31 and Caltech-256 ( C ) (Grifﬁn et al., 2007) datasets and is widely adopted in transfer learning methods (Long et al., 2013; Baktashmotlagh et al., 2013).”
Agnostic Federated Learning (2019, background): “(Gong et al., 2012; Long et al., 2015; Ganin and Lempitsky, 2015; Tzeng et al., 2015), or via lightly supervised ones (some amount of labeled data from the target domain) (Saenko et al.”
A Survey on Multi-Task Learning (2017, methodology): “Office-Caltech dataset [106]: The dataset contains data from 10 common categories shared in the Caltech-256 dataset and theOffice datasetwhich consists of images collected from three distinct domains/tasks: Amazon, Webcam and DSLR, making this dataset contain 4”
Domain Adaptation with Conditional Transferable Components (2016, methodology): “To obtain the shared representation, some methods firstly create intermediate representations by projecting the original feature to a series of subspaces and then concatenate them (Gopalan et al., 2011; Gong et al., 2012).”
Multi-Source Domain Adaptation: A Causal View (2015, methodology): “We also compared our approaches with alternatives on the object recognition data (Grifﬁn, Holub, and Perona 2007), as done by (Gong et al. 2012).”
Few-Shot Adversarial Domain Adaptation (2017, background): “Some try to find a function which can map from the source domain to the target domain [47, 28, 19, 16, 11, 55, 52].”
On Learning the Geodesic Path for Incremental Learning (2021, methodology): “The projection to subspaces has been used previously in domain adaptation [12, 13] and few-shot learning [36].”
Cross Modal Distillation for Supervision Transfer (2015, methodology): “In this section we present experimental results for the NYUD2 dataset where we use color and depth images as the paired modalities, and on the JHMDB video dataset for which we use the RGB and optical flow frames as the two modalities.”
Simultaneous Deep Transfer Across Domains and Tasks (2015, background): “A large number of methods have sought to overcome this difference by learning a feature space transformation to align the source and target representations [28, 23, 11, 15].”