paper-with-me

홈 › Papers

Domain Generalization by Mutual-Information Regularization with Pre-trained Models

2022-03-21 · Junbum Cha, Kyungjae Lee, Sungrae Park, Sanghyuk Chun

Domain generalization (DG) aims to learn a generalized model to an unseen target domain using only limited source domains. Previous attempts to DG fail to learn domain-invariant representations only from the source domains due to the significant domain shifts between training and test domains. Instead, we re-formulate the DG objective using mutual information with the oracle model, a model generalized to any possible domain. We derive a tractable variational lower bound via approximating the oracle model by a pre-trained model, called Mutual Information Regularization with Oracle (MIRO). Our extensive experiments show that MIRO significantly improves the out-of-distribution performance. Furthermore, our scaling experiments show that the larger the scale of the pre-trained model, the greater the performance improvement of MIRO. Source code is available at https://github.com/kakaobrain/miro.

📄 PDF Abstract BibTeX arXiv:2203.10789

Code (1)

kakaobrain/miro 공식 구현 pytorch

Tasks

Domain Generalization

Similar Papers 제목 키워드 기반

The Role of Mutual Information in Variational Classifiers

2020-10-22 · Matias Vera, Leonardo Rey Vega, Pablo Piantanida

Overfitting data is a well-known phenomenon related with the generation of a model that mimics too closely (or exactly) a particular instance of data, and may therefore fail to predict future observations reliably. In pr…

Variational Inference

Slicing Mutual Information Generalization Bounds for Neural Networks

2024-06-06 · Kimia Nadjahi, Kristjan Greenewald, Rickard Brüel Gabrielsson, Justin Solomon

The ability of machine learning (ML) algorithms to generalize well to unseen data has been studied through the lens of information theory, by bounding the generalization error with the input-output mutual information (MI…

Generalization BoundsModel Compression

Quadratic mutual information regularization in real-time deep CNN models

2021-08-26 · Maria Tzelepi, Anastasios Tefas

In this paper, regularized lightweight deep convolutional neural network models, capable of effectively operating in real-time on devices with restricted computational power for high-resolution video input are proposed. …

Binary Classification

Rate-Regularization and Generalization in VAEs

2019-11-11 · Alican Bozkurt, Babak Esmaeili, Jean-Baptiste Tristan, Dana H. Brooks 외

Variational autoencoders optimize an objective that combines a reconstruction loss (the distortion) and a KL term (the rate). The rate is an upper bound on the mutual information, which is often interpreted as a regulari…

Inductive Bias

RegMix: Adversarial Mutual and Generalization Regularization for Enhancing DNN Robustness

2025-10-06 · Zhenyu Liu, Varun Ojha arxiv

Adversarial training is the most effective defense against adversarial attacks. The effectiveness of the adversarial attacks has been on the design of its loss function and regularization term. The most widely used loss …

Knowledge DistillationAdversarial Robustness