Information Bottleneck Learning Using Privileged Information for Visual Recognition
By Saeid Motiian, Marco Piccirilli, D. Adjeroh, Gianfranco Doretto. 2016
54 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
- Gianfranco Doretto
- Saeid Motiian
- Juan Carlos Niebles
- Q. Jones
- Seyed Mehdi Iranmanesh
- Lu Jiang
- Eric P. Xing
- Ioannis A. Kakadiaris
In Computer Vision and Pattern Recognition
- Luc Van Gool
- Gianfranco Doretto
- Xiaogang Wang
- Li Fei-Fei
- Ming-Hsuan Yang
- Lu Jiang
- Juan Carlos Niebles
- Dacheng Tao
Citations in the corpus
- Few-Shot Adversarial Domain Adaptation (2017, methodology): “Others find a shared latent space that both domains can be mapped to before classification [35, 2, 39, 13, 14, 41, 37, 38].”
- Unified Deep Supervised Domain Adaptation and Generalization (2017, background): “Recently, [7, 42] have addressed UDA when an auxiliary data view [36, 43], is available during training, which is beyond the scope of this work.”
- Information Bottleneck Domain Adaptation with Privileged Information for Visual Recognition (2016, methodology): “F can be learned from the source training data with a projected gradient method [31], as described in [32].”
- Adaptive SVM+: Learning with Privileged Information for Domain Adaptation (2017, methodology): “We followed the same experimental procedure with [24, 29, 37] in which out of the 50 animal classes, we used the 10 testing classes for a total of 6,180 images.”
- Fast Generalized Distillation for Semi-Supervised Domain Adaptation (2017, methodology): “(Motiian et al. 2016) proposed the information bottleneck method with privileged information (IBPI) that leverage the auxiliary information such as supplemental visual features, bounding box annotations and 3D skeleton tracking data to improve visual recognition performance.”
- Graph Distillation for Action Detection with Privileged Modalities (2017, background): “Recently, the use of privileged information has been combined with deep learning in various settings such as PI reconstruction [49,57], information bottleneck [38], and Multi-Instance Multi-Label (MIML) learning [58].”