paper-with-me

홈 › Papers

Deeper, Broader and Artier Domain Generalization

2017-10-09 · ICCV 2017 10 · Da Li, Yongxin Yang, Yi-Zhe Song, Timothy M. Hospedales

The problem of domain generalization is to learn from multiple training domains, and extract a domain-agnostic model that can then be applied to an unseen domain. Domain generalization (DG) has a clear motivation in contexts where there are target domains with distinct characteristics, yet sparse data for training. For example recognition in sketch images, which are distinctly more abstract and rarer than photos. Nevertheless, DG methods have primarily been evaluated on photo-only benchmarks focusing on alleviating the dataset bias where both problems of domain distinctiveness and data sparsity can be minimal. We argue that these benchmarks are overly straightforward, and show that simple deep learning baselines perform surprisingly well on them. In this paper, we make two main contributions: Firstly, we build upon the favorable domain shift-robust properties of deep learning methods, and develop a low-rank parameterized CNN model for end-to-end DG learning. Secondly, we develop a DG benchmark dataset covering photo, sketch, cartoon and painting domains. This is both more practically relevant, and harder (bigger domain shift) than existing benchmarks. The results show that our method outperforms existing DG alternatives, and our dataset provides a more significant DG challenge to drive future research.

📄 PDF Abstract BibTeX arXiv:1710.03077

Code (6)

Evgeneus/Graph-Domain-Adaptaion pytorch
deeplearning-wisc/hypo pytorch
facebookresearch/DomainBed pytorch
facebookresearch/ModelRatatouille pytorch
hlzhang109/ddg pytorch
xch-liu/geom-tex-dg pytorch

Tasks

Domain Generalization

Similar Papers 제목 키워드 기반

CARTIER: Cartographic lAnguage Reasoning Targeted at Instruction Execution for Robots

2023-07-21 · Dmitriy Rivkin, Nikhil Kakodkar, Francois Hogan, Bobak H. Baghi 외

This work explores the capacity of large language models (LLMs) to address problems at the intersection of spatial planning and natural language interfaces for navigation. We focus on following complex instructions that …

Descriptive

Toric geometry of ReLU neural networks

2025-09-07 · Yaoying Fu arxiv

Given a continuous finitely piecewise linear function $f:\mathbb{R}^{n_0} \to \mathbb{R}$ and a fixed architecture $(n_0,\ldots,n_k;1)$ of feedforward ReLU neural networks, the exact function realization problem is to de…

What Variables Affect Out-of-Distribution Generalization in Pretrained Models?

2024-05-23 · Md Yousuf Harun, Kyungbok Lee, Jhair Gallardo, Giri Krishnan 외

Embeddings produced by pre-trained deep neural networks (DNNs) are widely used; however, their efficacy for downstream tasks can vary widely. We study the factors influencing transferability and out-of-distribution (OOD)…

Out-of-Distribution Generalization

Exploring Graph-Transformer Out-of-Distribution Generalization Abilities

2025-06-25 · Itay Niv, Neta Rabin

Deep learning on graphs has shown remarkable success across numerous applications, including social networks, bio-physics, traffic networks, and recommendation systems. Regardless of their successes, current methods freq…

Domain GeneralizationGraph LearningOut-of-Distribution GeneralizationRecommendation Systems

Is data-efficient learning feasible with quantum models?

2025-08-26 · Alona Sakhnenko, Christian B. Mendl, Jeanette M. Lorenz arxiv

The importance of analyzing nontrivial datasets when testing quantum machine learning (QML) models is becoming increasingly prominent in literature, yet a cohesive framework for understanding dataset characteristics rema…

Quantum Machine Learning