Adapting Visual Category Models to New Domains

By Kate Saenko, Brian Kulis, Mario Fritz, Trevor Darrell. 2010

3,219 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

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 Computer Vision and Pattern Recognition

Citations in the corpus

Learned in Translation: Contextualized Word Vectors (2017, background): “Saenko et al. [2010] adapt object recognition models developed for one visual domain to new imaging conditions by learning a transformation that minimizes domain-induced changes in the feature distribution.”
Predicting Deep Zero-Shot Convolutional Neural Networks Using Textual Descriptions (2015, background): “[23, 24] address the problem mentioned above where access to both source and target data are available at training time.”
DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition (2013, methodology): “…visual recognition challenges have tasks with few training examples; e.g., when a user is deﬁning a category “on-the-ﬂy” us-ing speciﬁc examples, or for ﬁne-grained recognition challenges (Welinder et al., 2010), attributes (Bourdev et al., 2011), and/or domain adaptation (Saenko et al., 2010).”
Unsupervised Domain Adaptation by Backpropagation (2014, methodology): “For the OFFICE dataset (Saenko et al., 2010), we directly compare the performance of our full network (feature extractor and label predictor) against recent DA approaches using previously published results.”
Rescaling Egocentric Vision: Collection, Pipeline and Challenges for EPIC-KITCHENS-100 (2020, methodology): “*: Note that Test* refers to ‘Target Test’ Dataset Train Test Classes SD M AAL Year Real/Syn Im a g e Office [105] 4110 N/A 31 1 3 N/A 2010 Real ImageCLEF [106] 2400 600 12 5 1 N/A 2014 Real Office↔ Home [107] 15500 N/A 65 4 1 N/A 2017 Real VisDA-C [108] 280157 N/A 12 3 1 N/A 2017 Real/Syn DomainNet”
Domain-Adversarial Training of Neural Networks (2015, background): “These include large-scale data sets of small images popular with deep learning methods, and the Office data sets (Saenko et al., 2010), which are a de facto standard for domain adaptation in computer vision, but have much fewer images.”
Adversarial Discriminative Domain Adaptation (2017, methodology): “Finally, we evaluate our method on the benchmark Office visual domain adaptation dataset [24].”
Learning Transferable Features with Deep Adaptation Networks (2015, methodology): “Accuracy on Office-31 dataset with classic unsupervised and semi-supervised adaptation protocols (Saenko et al., 2010).”
Marginalized Denoising Autoencoders for Domain Adaptation (2012, background): “Examples are computational biology (Liu et al., 2008), natural language processing (Daume III, 2007; McClosky et al., 2006) and computer vision (Saenko et al., 2010).”
A Theory of Multiple-Source Adaptation with Limited Target Labeled Data (2020, methodology): “We evaluated our algorithms and compared them to several baselines on the digits recognition dataset and the visual adaptation O ce dataset (Saenko et al., 2010).”
Agnostic Federated Learning (2019, background): “…unsupervised adaptation techniques (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., 2010; Yang et al., 2007; Hoffman et al., 2013; Girshick et al., 2014).”
Dataset Distillation (2018, background): “Extensive prior work has been proposed to adapt models to new tasks and datasets (Daume III, 2007; Saenko et al., 2010).”
Algorithms and Theory for Multiple-Source Adaptation (2018, methodology): “…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., 2010, Yang et al., 2007, Hoffman et al., 2013, Girshick et al., 2014], has been extensively investigated in the past.”
Learning to cluster in order to Transfer across domains and tasks (2017, background): “Ofﬁce-31 (Saenko et al., 2010) has images from 31 categories of ofﬁce objects.”
Few-Shot Adversarial Domain Adaptation (2017, methodology): “We present results using the Office dataset [47], the MNIST dataset [32], the USPS dataset [24], and the SVHN dataset [40].”