Multi-Domain Adversarial Learning - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2019

Multi-Domain Adversarial Learning

Alice Schoenauer Sebag
  • Function : Author
  • PersonId : 777603
  • IdRef : 192343408
Marc Schoenauer
Lani Wu
  • Function : Author

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.
Fichier principal
Vignette du fichier
MuLANNwithAuthors.pdf (4.94 Mo) Télécharger le fichier
Loading...

Dates and versions

hal-01968180 , version 1 (08-01-2019)

Identifiers

  • HAL Id : hal-01968180 , version 1

Cite

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⟩
498 View
948 Download

Share

Gmail Facebook X LinkedIn More