AdaGraph: Unifying Predictive and Continuous Domain Adaptation Through Graphs

By Massimiliano Mancini, Samuel Rota Bulò, Barbara Caputo, Elisa Ricci. 2019

77 citations recorded by the source corpus.

The ability to categorize is a cornerstone of visual intelligence, and a key functionality for artificial, autonomous visual machines. This problem will never be solved without algorithms able to adapt and generalize across visual domains. Within the context of domain adaptation and generalization, this paper focuses on the predictive domain adaptation scenario, namely the case where no target data are available and the system has to learn to generalize from annotated source images plus unlabeled samples with associated metadata from auxiliary domains. Our contribution is the first deep architecture that tackles predictive domain adaptation, able to leverage over the information brought by the auxiliary domains through a graph. Moreover, we present a simple yet effective strategy that allows us to take advantage of the incoming target data at test time, in a continuous domain adaptation scenario. Experiments on three benchmark databases support the value of our approach.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Infectious Diseases

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Learngene: From Open-World to Your Learning Task (2021, background): “Moreover, continual domain adaptation (Zhao and Hoi 2010; Liu et al. 2020; Bitarafan, Baghshah, and Gheisari 2016; Wang, He, and Katabi 2020; Mancini et al. 2019a) enables the learner to adapt to continually evolving target domains without forgetting.”
Open Compound Domain Adaptation (2019, background): “The goal is to extend unsupervised domain adaptation to latent [16, 51, 32] or multiple [11, 9, 54] or continuous [2, 13, 31, 50] target domains, when only the source domain has class labels.”
Continuous Domain Adaptation with Variational Domain-Agnostic Feature Replay (2020, background): “For example, (Mancini et al., 2019) attempt to solve a specific scenario in continuous domain adaptation, where no target data is available, but with metadata provided for all domains; (Gong et al., 2019) propose to bridge two domains by generating a continuous flow of intermediate domains between…”
Generalized Source-free Domain Adaptation (2021, methodology): “Recently, a few works [4, 26, 36] have emerged that aim to tackle the Continual Domain Adaptation (CDA) problem.”
Gradient Regularized Contrastive Learning for Continual Domain Adaptation (2020, methodology): “The approaches (Mancini et al. 2019; Gong et al. 2019; Wulfmeier, Bewley, and Posner 2018; Hoffman et al. 2014) do not explicitly target the catastrophic forgetting problem, while the approaches (Bobu et al.”