Poster
Multi-Domain Adversarial Learning
Alice Schoenauer Sebag · Louise E Heinrich · Marc Schoenauer · Michele Sebag · Lani Wu · Steven Altschuler
Great Hall BC #28
Keywords: [ domain adaptation ] [ adversarial learning ] [ multi-domain learning ] [ h-divergence ] [ deep representation learning ] [ high-content microscopy ]
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.
Live content is unavailable. Log in and register to view live content