Skip to Main content Skip to Navigation
New interface
Conference papers

Multi-Domain Adversarial Learning

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.
Document type :
Conference papers
Complete list of metadata

Cited literature [78 references]  Display  Hide  Download
Contributor : Marc Schoenauer Connect in order to contact the contributor
Submitted on : Tuesday, January 8, 2019 - 12:24:07 AM
Last modification on : Tuesday, November 29, 2022 - 12:02:10 PM
Long-term archiving on: : Tuesday, April 9, 2019 - 1:09:16 PM


  • HAL Id : hal-01968180, version 1


Alice Schoenauer Sebag, Louise Heinrich, Marc Schoenauer, Michèle Sebag, Lani Wu, et al.. Multi-Domain Adversarial Learning. ICLR 2019 - Seventh annual International Conference on Learning Representations, Tara Sainath, May 2019, New Orleans, United States. ⟨hal-01968180⟩



Record views


Files downloads