Learning from Extrinsic and Intrinsic Supervisions for Domain Generalization

by   Shujun Wang, et al.

The generalization capability of neural networks across domains is crucial for real-world applications. We argue that a generalized object recognition system should well understand the relationships among different images and also the images themselves at the same time. To this end, we present a new domain generalization framework that learns how to generalize across domains simultaneously from extrinsic relationship supervision and intrinsic self-supervision for images from multi-source domains. To be specific, we formulate our framework with feature embedding using a multi-task learning paradigm. Besides conducting the common supervised recognition task, we seamlessly integrate a momentum metric learning task and a self-supervised auxiliary task to collectively utilize the extrinsic supervision and intrinsic supervision. Also, we develop an effective momentum metric learning scheme with K-hard negative mining to boost the network to capture image relationship for domain generalization. We demonstrate the effectiveness of our approach on two standard object recognition benchmarks VLCS and PACS, and show that our methods achieve state-of-the-art performance.


page 1

page 2

page 3

page 4


Improving out-of-distribution generalization via multi-task self-supervised pretraining

Self-supervised feature representations have been shown to be useful for...

Domain Generalization via Model-Agnostic Learning of Semantic Features

Generalization capability to unseen domains is crucial for machine learn...

Domain Generalization for Object Recognition with Multi-task Autoencoders

The problem of domain generalization is to take knowledge acquired from ...

Label Efficient Learning of Transferable Representations across Domains and Tasks

We propose a framework that learns a representation transferable across ...

Deep Supervision with Intermediate Concepts

Recent data-driven approaches to scene interpretation predominantly pose...

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

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

INDIGO: Intrinsic Multimodality for Domain Generalization

For models to generalize under unseen domains (a.k.a domain generalizati...