Learning Transferrable Representations for Unsupervised Domain Adaptation

By Ozan Sener, Hyun Oh Song, Ashutosh Saxena, Silvio Savarese. 2016

283 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Learning to cluster in order to Transfer across domains and tasks (2017, background): “…of work dealing with domain shift between image datasets by minimizing domain discrepancy (Tzeng et al., 2014; Long et al., 2015b; Ganin et al., 2016; Sun et al., 2016; Long et al., 2016; Sener et al., 2016; Carlucci et al., 2017; Long et al., 2017; Zellinger et al., 2017; Bousmalis et al., 2017).”
Adversarial Examples, Uncertainty, and Transfer Testing Robustness in Gaussian Process Hybrid Deep Networks (2017, background): “Closely related to this is the idea of domain adaptation where you ﬁne tune models on a new domain [18, 52].”
Gibson Env: Real-World Perception for Embodied Agents (2018, background): “Therefore, we instead formulate the rendering problem as forming a joint space ensuring a correspondence between rendered and real images, and consequently, dissolving the gap [77].”
Learning Metrics From Teachers: Compact Networks for Image Embedding (2019, background): “Furthermore, embedding networks are essential for computer vision, as evidenced by the large variety of tasks in which they are used, including feature-based object retrieval [9], face recognition [25], feature matching [6], domain adaptation [27], weakly supervised learning [36], ranking [35], or z”
Contrastive Adaptation Network for Unsupervised Domain Adaptation (2019, background): “Some previous works pay efforts to learn more disciminative features while performing domain alignment [30, 12, 26, 27, 23].”
No More Discrimination: Cross City Adaptation of Road Scene Segmenters (2017, background): “[33] enforce cyclic consistency on adaptation and structured consistency on transduction in their framework.”
Domain Adaptive Faster R-CNN for Object Detection in the Wild (2018, background): “Domain Adaptation: Domain adaptation has been widely studied for image classification in computer vision [10, 11, 33, 23, 22, 14, 52, 40, 15, 18, 50, 45, 43, 35].”
Beyond Sharing Weights for Deep Domain Adaptation (2016, background): “Finally, another class ofmethods use pseudo labels to facilitate domain adaptation [50], [51].”
Universal Domain Adaptation through Self Supervision (2020, unknown): “Clustering-based methods are proposed by (Deng et al., 2019; Sener et al., 2016; Haeusser et al., 2017).”
Learning Semantic Segmentation From Synthetic Data: A Geometrically Guided Input-Output Adaptation Approach (2018, background): “It is mostly studied in image recognition problems by both conventional approaches [29, 18, 15, 10, 33] and CNN-based approaches [36, 12, 14, 50, 42, 39, 31, 19, 37, 38].”
FDA: Fourier Domain Adaptation for Semantic Segmentation (2020, background): “Alignment in high-level feature space [27, 16, 36, 38, 31] can be counter-productive for semantic segmentation, unlike image-level classification, [20, 28, 37], due to the complex representations and the difficulty in stabilizing adversarial training.”
Zero-Shot Task Transfer (2019, methodology): “ain with limited data [27][9]. Learning domain-invariant features requires domain alignment. Such matching is done either by mid-level features of a CNN [14], using an autoencoder [14], by clustering [36], or more recently, by using generative adversarial networks [24]. In some recent efforts [35][6”
Automatic autonomous vision-based power line inspection: A review of current status and the potential role of deep learning (2018, background): “adaptation [73, 74, 75, 76], which is capable of adapting models trained only on synthetic images and/or images from related tasks to use on the target task, is a potential solution.”
Asymmetric Tri-training for Unsupervised Domain Adaptation (2017, methodology): “Baseline Methods We compare our method with ﬁve methods for unsupervised domain adaptation including state-of-the art methods in visual domain adaptation; Maximum Mean Discrepancy (MMD) (Long et al., 2015b), Domain Adversarial Neural Network (DANN) (Ganin & Lempitsky, 2014), Deep Reconstruction Clas”
Progressive Feature Alignment for Unsupervised Domain Adaptation (2018, methodology): “[3, 5, 23, 34, 32, 44, 41] utilize the pseudo-labels to compensate the lack of categorical information in the target domain.”
Adversarial Discriminative Domain Adaptation (2017, background): “In the case of unlabeled target domains (the focus of this paper) the main strategy has been to guide feature learning by minimizing the difference between the source and target feature distributions [11, 12, 5, 6, 8, 9, 13, 14].”
A Survey of Unsupervised Deep Domain Adaptation (2018, methodology): “e-training the model using the labels (a form of self-training). Wei et al. [250] in GAGL alternate between feeding in real source and target data and the fake images generated by a GAN. Sener et al. [214] alternate between k-nearest neighbors and performing gradient descent. 4.5 Multi-Level Some ad”
Deep Metric Learning via Facility Location (2016, background): “Learning to measure the similarity among arbitrary groups of data is of great practical importance, and can be used for a variety of tasks such as feature based retrieval [30], clustering [10], near duplicate detection [41], verification [3, 4], feature matching [6], domain adaptation [27], video ba”
Generalizing a Person Retrieval Model Hetero- and Homogeneously (2018, methodology): “Several methods utilize similarity of features to give pseudo-labels to unlabeled target samples [13,14].”