Multi-Domain Adversarial Learning

By Alice Schoenauer Sebag, Louise Heinrich, Marc Schoenauer, Michèle Sebag, Lani F. Wu, Steven J. Altschuler. 2019

65 citations recorded by the source corpus.

Author(s): Schoenauer-Sebag, Alice; Heinrich, Louise; Schoenauer, Marc; Sebag, Michele; Wu, Lani F; Altschuler, Steve J | Abstract: Multi-domain learning (MDL) aims at obtaining a model with minimal average risk across multiple domains. Our empirical motivation is automated microscopy data, where cultured cells are imaged after being exposed to known and unknown chemical perturbations, and each dataset displays significant experimental bias. This paper presents a multi-domain adversarial learning approach, MuLANN, to leverage multiple datasets with overlapping but distinct class sets, in a semi-supervised setting. Our contributions include: i) a bound on the average- and worst-domain risk in MDL, obtained using the H-divergence; ii) a new loss to accommodate semi-supervised multi-domain learning and domain adaptation; iii) the experimental validation of the approach, improving on the state of the art on two standard image benchmarks, and a novel bioimage dataset, Cell.

Subfields: Computer Vision and Pattern Recognition, 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 Computer Vision and Pattern Recognition

In Representation & Self-Supervised Learning

Citations in the corpus

Learning Robust Global Representations by Penalizing Local Predictive Power (2019, background): “, 2018) and coercing domain invariance via adversarial learning (or further extensions) (Ganin et al., 2016; Bousmalis et al., 2017; Tzeng et al., 2017; Xie et al., 2018; Hoffman et al., 2018; Long et al., 2018; Zhao et al., 2018b; Kumar et al., 2018; Li et al., 2018b; Zhao et al., 2018a; Schoenauer”
Estimating Counterfactual Treatment Outcomes over Time Through Adversarially Balanced Representations (2020, methodology): “…To achieve this and to estimate counterfactual outcomes under a planned sequence of treatments, we integrate the domain adversarial training framework proposed by Ganin et al. (2016) and extended by Sebag et al. (2019) to the multi-domain learning setting, into a sequence-to-sequence architecture.”
A Survey of Unsupervised Deep Domain Adaptation (2018, background): “Some researchers have developed adversarial strategies to tackle this multi-domain learning challenge [90, 212].”
Domain Generalization Using a Mixture of Multiple Latent Domains (2019, methodology): “Although these methods assume single-source and target domains, multi-source domain adaptation methods (Xu et al. 2018; Schoenauer-Sebag et al. 2019) utilize multiple source domains for domain adaptation to learn domain relations.”
CHAOS Challenge - Combined (CT-MR) Healthy Abdominal Organ Segmentation (2020, unknown): “world clinical scenarios, it is essential to facilitate from recent DL research directions like improving generalization through domain adaptation strategies (Yang et al., 2019; Gholami et al., 2019; Schoenauer-Sebag et al., 2019), optimizing neural network architecture to reduce computational cost ”
Domain Aggregation Networks for Multi-Source Domain Adaptation (2019, unknown): “, 2018) and Known Unknown Discrimination (Schoenauer-Sebag et al., 2019).”