DeepAI AI Chat
Log In Sign Up

Self-Supervised Learning Across Domains

by   Silvia Bucci, et al.

Human adaptability relies crucially on learning and merging knowledge from both supervised and unsupervised tasks: the parents point out few important concepts, but then the children fill in the gaps on their own. This is particularly effective, because supervised learning can never be exhaustive and thus learning autonomously allows to discover invariances and regularities that help to generalize. In this paper we propose to apply a similar approach to the problem of object recognition across domains: our model learns the semantic labels in a supervised fashion, and broadens its understanding of the data by learning from self-supervised signals on the same images. This secondary task helps the network to learn the concepts like spatial orientation and part correlation, while acting as a regularizer for the classification task. Extensive experiments confirm our intuition and show that our multi-task method combining supervised and self-supervised knowledge shows competitive results with respect to more complex domain generalization and adaptation solutions. It also proves its potential in the novel and challenging predictive and partial domain adaptation scenarios.


page 1

page 2

page 7

page 9


Domain Generalization by Solving Jigsaw Puzzles

Human adaptability relies crucially on the ability to learn and merge kn...

LLEDA – Lifelong Self-Supervised Domain Adaptation

Lifelong domain adaptation remains a challenging task in machine learnin...

Self-Supervised Graph Neural Network for Multi-Source Domain Adaptation

Domain adaptation (DA) tries to tackle the scenarios when the test data ...

Generic network for domain adaptation based on self-supervised learning and deep clustering

Domain adaptation methods train a model to find similar feature represen...

Self-Supervised Learning for Domain Adaptation on Point-Clouds

Self-supervised learning (SSL) allows to learn useful representations fr...

What My Motion tells me about Your Pose: Self-Supervised Fine-Tuning of Observed Vehicle Orientation Angle

The determination of the relative 6 Degree of Freedom (DoF) pose of vehi...

Learning to Generalize One Sample at a Time with Self-Supervision

Although deep networks have significantly increased the performance of v...