DeepAI AI Chat
Log In Sign Up

Dynamic Adaptation on Non-Stationary Visual Domains

by   Sindi Shkodrani, et al.

Domain adaptation aims to learn models on a supervised source domain that perform well on an unsupervised target. Prior work has examined domain adaptation in the context of stationary domain shifts, i.e. static data sets. However, with large-scale or dynamic data sources, data from a defined domain is not usually available all at once. For instance, in a streaming data scenario, dataset statistics effectively become a function of time. We introduce a framework for adaptation over non-stationary distribution shifts applicable to large-scale and streaming data scenarios. The model is adapted sequentially over incoming unsupervised streaming data batches. This enables improvements over several batches without the need for any additionally annotated data. To demonstrate the effectiveness of our proposed framework, we modify associative domain adaptation to work well on source and target data batches with unequal class distributions. We apply our method to several adaptation benchmark datasets for classification and show improved classifier accuracy not only for the currently adapted batch, but also when applied on future stream batches. Furthermore, we show the applicability of our associative learning modifications to semantic segmentation, where we achieve competitive results.


page 1

page 2


Continuous Domain Adaptation with Variational Domain-Agnostic Feature Replay

Learning in non-stationary environments is one of the biggest challenges...

Lightweight Conditional Model Extrapolation for Streaming Data under Class-Prior Shift

We introduce LIMES, a new method for learning with non-stationary stream...

The Norm Must Go On: Dynamic Unsupervised Domain Adaptation by Normalization

Domain adaptation is crucial to adapt a learned model to new scenarios, ...

Source Domain Subset Sampling for Semi-Supervised Domain Adaptation in Semantic Segmentation

In this paper, we introduce source domain subset sampling (SDSS) as a ne...

Online Adaptation of Deep Architectures with Reinforcement Learning

Online learning has become crucial to many problems in machine learning....

Learning Manifolds from Non-stationary Streaming Data

Streaming adaptations of manifold learning based dimensionality reductio...