DeepAI AI Chat
Log In Sign Up

Agnostic Domain Generalization

by   Fabio M. Carlucci, et al.
HUAWEI Technologies Co., Ltd.
Politecnico di Torino
Sapienza University of Rome

The ability to generalize across visual domains is crucial for the robustness of visual recognition systems in the wild. Several works have been dedicated to close the gap between a single labeled source domain and a target domain with transductive access to its data. In this paper we focus on the wider domain generalization task involving multiple sources and seamlessly extending to unsupervised domain adaptation when unlabeled target samples are available at training time. We propose a hybrid architecture that we name ADAGE: it gracefully maps different source data towards an agnostic visual domain through pixel-adaptation based on a novel incremental architecture, and closes the remaining domain gap through feature adaptation. Both the adaptive processes are guided by adversarial learning. Extensive experiments show remarkable improvements compared to the state of the art.


page 8

page 13


Adversarial Robustness for Unsupervised Domain Adaptation

Extensive Unsupervised Domain Adaptation (UDA) studies have shown great ...

Certainty Volume Prediction for Unsupervised Domain Adaptation

Unsupervised domain adaptation (UDA) deals with the problem of classifyi...

Kitting in the Wild through Online Domain Adaptation

Technological developments call for increasing perception and action cap...

Best sources forward: domain generalization through source-specific nets

A long standing problem in visual object categorization is the ability o...

Domain Generalization with Domain-Specific Aggregation Modules

Visual recognition systems are meant to work in the real world. For this...

AdaGraph: Unifying Predictive and ContinuousDomain Adaptation through Graphs

The ability to categorize is a cornerstone of visual intelligence, and a...

AU-Guided Unsupervised Domain Adaptive Facial Expression Recognition

The domain diversities including inconsistent annotation and varied imag...