Deep Domain Generalization With Structured Low-Rank Constraint

By Zhengming Ding, Yun Raymond Fu. 2018

145 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Ocean Engineering, 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

1. Eric P. Xing
2. Haohan Wang
3. Yoshua Bengio
4. Zachary Chase Lipton
5. David Lopez-Paz
6. Mohit Bansal
7. Barbara Caputo
8. Jiashi Feng

In Ocean Engineering

1. David Lopez-Paz
2. Eric P. Xing
3. Tatsuya Harada
4. Ishaan Gulrajani
5. Zachary Chase Lipton

In Representation & Self-Supervised Learning

1. Haohan Wang
2. Eric P. Xing
3. Tatsuya Harada
4. Barbara Caputo
5. Zachary Chase Lipton
6. David Lopez-Paz
7. Ishaan Gulrajani
8. Toshihiko Matsuura

Citations in the corpus

• Learning Robust Global Representations by Penalizing Local Predictive Power (2019, background): “, 2018), or build ensembles of per-domain models that are then fused representations together (Bousmalis et al., 2016; Ding and Fu, 2018; Mancini et al., 2018).”
• Learning Robust Representations by Projecting Superficial Statistics Out (2018, background): “…through adversarial (or similar) techniques (Ghifary et al., 2015; Wang et al., 2016; Motiian et al., 2017; Li et al., 2018; Carlucci et al., 2018), or building an ensemble of one-for-each-domain deep models and then fusing representations together (Ding & Fu, 2018; Mancini et al., 2018).”
• In Search of Lost Domain Generalization (2020, methodology): “Dou et al. (2019) use a similar MAML strategy, together with two regularizers that encourage features from different domains to respect inter-class relationships, and be compactly clustered by class labels.”
• Deep Unsupervised Domain Adaptation: A Review of Recent Advances and Perspectives (2022, background): “Ding and Fu (2017) propose to match the low-rank structure of domain-specific features.”
• Domain Generalization Using a Mixture of Multiple Latent Domains (2019, background): “SLRC (Ding and Fu 2018): The structured lowrank constraint to transfer the knowledge between domainspecific networks and the domain-invariant one.”
• Domain Generalization by Solving Jigsaw Puzzles (2019, background): “SLRC [13] is based on a single domain invariant network and multiple domain specific ones and it applies a low rank constraint among them.”
• Deep Stable Learning for Out-Of-Distribution Generalization (2021, background): “Some pioneering methods require clear and significant heterogeneity, namely that the domains are manually divided and labeled [61, 16, 46, 9, 42], which cannot be always satisfied in real applications.”