Timezone: »

 
Multi-Domain Long-Tailed Learning by Augmenting Disentangled Representations
Huaxiu Yao · Xinyu Yang · Allan Zhou · Chelsea Finn

@
in Workshop on Distribution Shifts: Connecting Methods and Applications »
Event URL: https://openreview.net/forum?id=MX7O-4G4io »

There is an inescapable long-tailed class-imbalance issue in many real-world classification problems. Existing long-tailed classification methods focus on the single-domain setting, where all examples are drawn from the same distribution. However, real-world scenarios often involve multiple domains with distinct imbalanced class distributions. We study this multi-domain long-tailed learning problem and aim to produce a model that generalizes well across all classes and domains. Towards that goal, we introduce TALLY, which produces invariant predictors by balanced augmenting hidden representations over domains and classes. Built upon a proposed selective balanced sampling strategy, TALLY achieves this by mixing the semantic representation of one example with the domain-associated nuisances of another, producing a new representation for use as data augmentation. To improve the disentanglement of semantic representations, TALLY further utilizes a domain-invariant class prototype that averages out domain-specific effects. We evaluate TALLY on four long-tailed variants of classical domain generalization benchmarks and two real-world imbalanced multi-domain datasets. The results indicate that TALLY consistently outperforms other state-of-the-art methods in both subpopulation shift and domain shift.

Author Information

Huaxiu Yao (Stanford University)
Xinyu Yang (Shanghai Jiaotong University)
Allan Zhou (Stanford University)
Chelsea Finn (Stanford)

More from the Same Authors