Open Set Domain Adaptation

By Pau Panareda Busto, Juergen Gall. 2017

633 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

Recognition in Terra Incognita (2018, methodology): “using a multi-task setting where the adaptation was from clean web images to real-world images, and [44] investigated open-set domain adaptation.”
Prototype-Guided Continual Adaptation for Class-Incremental Unsupervised Domain Adaptation (2022, background): “In this field, the most common task is closed-set UDA [33] which assumes that source and target domains share the same set of classes.”
Class-Incremental Domain Adaptation (2020, background): “a is proprietary [24,32,34] (e.g. in a self-driving car), or simply unavailable during model upgrade [7,23,28]. Moreover, these methods can only detect new target categories as a single unknown class [36], and cannot assign individual semantic labels to such categories (Fig. 1C). Thus, these methods”
Recent Advances in Open Set Recognition: A Survey (2018, background): “For example, [155]–[157] have introduced this scenario into domain adaptation, while [158] introduced it to the semantic instance segmentation task.”
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].”
Overcoming Negative Transfer: A Survey (2020, methodology): “And similar negative effects have also been observed in various settings including imbalanced distributions [33] and open set transfer learning [49].”
Temporal Attentive Alignment for Large-Scale Video Domain Adaptation (2019, methodology): “ply TA(3)N to different cross-domain video tasks, including video captioning, segmentation, and detection; 2) we would like to extend these methods to the open-set setting [1, 39, 33, 15], which has different categories between source and target domains.”
Invariance Matters: Exemplar Memory for Domain Adaptive Person Re-Identification (2019, methodology): “UDA in person re-ID is an open set problem [3] which is more challenging than closedset one.”
Under review as a conference paper at ICLR 2020 many domain adaptation methods (2019, background): “Recently, several works Saito et al. (2018); Panareda Busto & Gall (2017); Tan et al. (2019) address the open set domain adaptation.”
WildFish: A Large Benchmark for Fish Recognition in the Wild (2018, background): “Recently, the remarkable successes of convolutional neural networks (CNNs) [9, 18, 20, 24, 37, 38, 45] have promoted open-set deep learning [4, 6, 16, 36] and its relevant applications such as person re-identification [51], face recognition [17], scene parsing [49].”
A Survey on Negative Transfer (2020, background): “[103] found that the source model trained with a simple balance sampling strategy can significantly reduce label shift in source-free TL.”
Separate to Adapt: Open Set Domain Adaptation via Progressive Separation (2019, methodology): “Therefore we manually choose the hyper-parameter λ of ATI-λ by cross-validation.”
ROAD: Reality Oriented Adaptation for Semantic Segmentation of Urban Scenes (2017, background): “Recent works aim to improve the domain adaptability of deep neural networks, including [26, 8, 9, 36, 30, 29, 22, 14, 27, 28].”
Multiple Class Novelty Detection Under Data Distribution Shift (2020, background): “Moreover, we discuss the differences between the closely related problem setting such as open-set domain adaptation [36] and also provide experimental analysis to show that their performance is sub-optimal in the problem setting considered in this paper.”
Unsupervised Domain Adaptation of Object Detectors: A Survey (2021, background): “Hence, it is important to mitigate the problem of negative transfer by down-weighting the data samples from classes that are not common between the domain, thereby promoting feature alignment only in the shared label spaces (positive transfer) [185], [186], [187], [188], [189].”
Learning to Transfer Examples for Partial Domain Adaptation (2019, background): “Unlike OSDA, in our scenario the target classes are entirely unknown at training.”
Heterogeneous Domain Generalization Via Domain Mixup (2020, background): “Compared with the aforementioned two tasks, open set domain adaptation (OSDA) [7] is more challenging as it sets private labels as an ”unknown” class.”