Visual Domain Adaptation: A survey of recent advances

By Vishal M. Patel, Raghuraman Gopalan, Ruonan Li, Ramalingam Chellappa. 2015

884 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Radiology, Nuclear Medicine and Imaging, 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 Computer Vision and Pattern Recognition

In Radiology, Nuclear Medicine and Imaging

In Representation & Self-Supervised Learning

Citations in the corpus

Knowledge Flow: Improve Upon Your Teachers (2019, background): “…particularly in reinforcement learning, teachers have also been considered in one way or another by Rusu et al. (2016b); Fernando et al. (2017); Wang et al. (2017); Li & Hoiem (2016); Bengio et al. (2009); Patel et al. (2015); Chen & Liu (2016); Teh et al. (2017); Parisotto et al. (2016).”
Less-forgetting Learning in Deep Neural Networks (2016, methodology): “Usually, the network pre-trained using the original data (source domain) is used as initial weights for adapting to the new data (target domain) [6], [7].”
The limits and potentials of deep learning for robotics (2018, background): “To address this domain adaptation problem [23], [30], [83], a robotic vision system should be able to learn from new training samples of known classes during deployment and adopt its internal representations accordingly.”
Generalisation in humans and deep neural networks (2018, background): “At the exciting interface between cognitive science / visual perception and deep learning, inspiration and ideas may come from both fields: While the computer vision sub-area of domain adaptation (see [63] for a review) is working on robust machine inference in spite of shifts in the input distribut”
Continual Learning for Robotics (2019, background): “In computer vision, transferring what has been learned from a past environment to new environments would be often referred to as domain adaptation (Patel et al., 2015; Csurka, 2017).”
Using Simulation and Domain Adaptation to Improve Efficiency of Deep Robotic Grasping (2018, background): “main. In our case the source domain is the simulation, whereas the target is the real world. There has recently been a signiﬁcant amount of work on domain adaptation, particularly for computer vision [16], [17]. Prior work can be grouped into two main types: feature-level and pixel-level adaptation.”
Learning to Generalize: Meta-Learning for Domain Generalization (2017, neutral): “DA is relatively well studied, and addresses using unlabeled or sparsely labeled data in the target domain to quickly adapt a model trained in a different source domain (Patel et al. 2015; Csurka 2017).”
In Search of Lost Domain Generalization (2020, background): “In the latter, it is assumed that unlabeled data from the test domain is available during training [Pan and Yang, 2009, Patel et al., 2015, Wilson and Cook, 2018].”
Deep Hashing Network for Unsupervised Domain Adaptation (2017, background): “A survey of popular domain adaptation techniques for computer vision is provided in [41] and a more generic survey of transfer learning approaches can be found in [39].”
Recent Advances in Open Set Recognition: A Survey (2018, background): “[3]–[5], domain adaptation [6], [7], zero-shot [8]–[10], oneshot (few-shot) [11]–[20] recognition/learning and open set recognition/classification [21]–[23], and so forth.”
Sim-To-Real via Sim-To-Sim: Data-Efficient Robotic Grasping via Randomized-To-Canonical Adaptation Networks (2018, background): “Visual domain adaptation [42, 13] is a process that allows a machine learning model trained with samples from a source domain to generalize to a target domain, by utilizing existing but (mostly) unlabeled target data.”
Deep Reconstruction-Classification Networks for Unsupervised Domain Adaptation (2016, background): “Although domain adaptation has gained increasing attention in object recognition, see [3] for a recent overview, the problem remains essentially unsolved since model accuracy has yet to reach a level that is satisfactory for real-world applications.”
Lifelong Teacher-Student Network Learning (2021, methodology): “The theoretical analysis is inspired by the domain adaptation theory [10], [46], where error bounds are evaluated for the transfer of information from one data domain to another in learning systems.”
Detach and Adapt: Learning Cross-Domain Disentangled Deep Representation (2017, background): “quires the advance of transfer learning [26] or domain adaptation [27] techniques to address this challenging yet practical problem.”
Generalized ODIN: Detecting Out-of-Distribution Image Without Learning From Out-of-Distribution Data (2020, background): “Such shift is also a scenario be widely discussed in the problem of domain adaptation [30, 31].”
Domain Adaptation for Semantic Segmentation of Urban Scenes (2017, background): “The existing work on domain adaptation mostly focuses on classification and regression problems [43, 41], e.”