Tabula rasa: Model transfer for object category detection

By Yusuf Aytar, Andrew Zisserman. 2011

361 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

One-Shot Imitation Learning (2017, background): “Success stories include domain adaptation in computer vision [64, 34, 28, 4, 15, 24, 33, 59, 14] and control [60, 45, 46, 20, 54].”
SoundNet: Learning Sound Representations from Unlabeled Video (2016, background): “Transfer Learning: Transfer learning is widely studied within computer vision such as transferring knowledge for object detection [1, 2] and segmentation [18], however transferring from vision to other modalities are only possible recently with the emergence of high performance visual models [33, 17”
Few-Shot Adversarial Domain Adaptation (2017, methodology): “Finally, some use regularization to improve the fit on the target domain [4, 1, 62, 10, 3, 8].”
Cross Modal Distillation for Supervision Transfer (2015, methodology): “Acknowledgments: The authors would like to thank Georgia Gkioxari for sharing her wisdom and experimental setup for the UCF 101 and JHMDB datasets.”
Simultaneous Deep Transfer Across Domains and Tasks (2015, background): “For the supervised adaptation scenario, when a limited amount of labeled data is available in the target domain, some approaches have been proposed to learn a target classiﬁer regularized against the source clas-siﬁer [32, 2, 1].”
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.”
Third-Person Imitation Learning (2017, background): “…of adapting what is learned in one domain to another domain has been studied extensively in computer vision in the supervised learning setting Yang et al. (2007); Mansour et al. (2009); Kulis et al. (2011); Aytar & Zisserman (2011); Duan et al. (2012); Hoffman et al. (2013); Long & Wang (2015).”
Taskonomy: Disentangling Task Transfer Learning (2018, background): “Domain adaption seeks to render a function that is developed on a certain domain applicable to another [42, 96, 5, 77, 50, 24, 34].”
Efficient Learning of Domain-invariant Image Representations (2013, methodology): “We compare against pmt-svm [10] and ARC-t [12] using both knn and svm classification.”
One-Shot Imitation from Observing Humans via Domain-Adaptive Meta-Learning (2018, background): “within the machine learning community, especially for varying visual domains [3, 33] and visual shift between simulation and reality [56, 41].”
Deep Hashing Network for Unsupervised Domain Adaptation (2017, methodology): “One straightforward approach is, to modify a classifier trained for the source data by adapting it to classify target data [1, 4] or learn a transformation matrix to linearly transform the source data, so that it is aligned with the target [27, 42].”
One-Shot Adaptation of Supervised Deep Convolutional Models (2013, methodology): “In particular, MMDT minimizes the following loss function (assuming a binary classification task to simplify notation, and with `hinge defined as in PMT): LMMDT (θ, A) = 1 2 ‖θ‖22 + 1 2 ‖A− I‖2F + Cs`hinge(X,Y ;θ) + Ct`hinge(AX̃, Ỹ ;θ) , (2) where Cs and Ct are hyperparameters controlling the impor”
Unified Deep Supervised Domain Adaptation and Generalization (2017, background): “The third one regularizes a classifier trained on a source distribution to work well on a target distribution [4, 1, 66, 15, 3, 12].”
Domain Adaptation for Visual Applications: A Comprehensive Survey (2017, methodology): “the appearance based classiﬁers to adapt to the target domain the models trained on the source domain. The Projective Model Transfer SVM (PMT-SVM) and the Deformable Adaptive SVM (DA-SVM) proposed in [195] are such methods, which adapt HOG deformable source templates [196, 197] with labeled target b”
Adapting Deep Visuomotor Representations with Weak Pairwise Constraints (2015, methodology): “used for both visual domains and adaptation took the form of learning a transformation between the two spaces [18], [19], [20] or regularizing the target domain model based on the source domain [21], [22]. Further models improved upon this by proposing adaptation which both transformed the represent”
Explicit Inductive Bias for Transfer Learning with Convolutional Networks (2018, methodology): “Hence, the network capacity has not to be restricted blindly: the pre-trained model sets a reference that can be used to deﬁne the functional space effectively explored during ﬁne-tuning.”