Back-to-Bones: Rediscovering the Role of Backbones in Domain
Generalization
- URL: http://arxiv.org/abs/2209.01121v2
- Date: Tue, 9 May 2023 14:31:36 GMT
- Title: Back-to-Bones: Rediscovering the Role of Backbones in Domain
Generalization
- Authors: Simone Angarano, Mauro Martini, Francesco Salvetti, Vittorio Mazzia,
Marcello Chiaberge
- Abstract summary: Domain Generalization studies the capability of a deep learning model to generalize to out-of-training distributions.
Recent research has provided a reproducible benchmark for DG, pointing out the effectiveness of naive empirical risk minimization (ERM) over existing algorithms.
In this paper, we evaluate the backbones proposing a comprehensive analysis of their intrinsic generalization capabilities.
- Score: 1.6799377888527687
- License: http://creativecommons.org/licenses/by-nc-sa/4.0/
- Abstract: Domain Generalization (DG) studies the capability of a deep learning model to
generalize to out-of-training distributions. In the last decade, literature has
been massively filled with training methodologies that claim to obtain more
abstract and robust data representations to tackle domain shifts. Recent
research has provided a reproducible benchmark for DG, pointing out the
effectiveness of naive empirical risk minimization (ERM) over existing
algorithms. Nevertheless, researchers persist in using the same outdated
feature extractors, and no attention has been given to the effects of different
backbones yet. In this paper, we start back to the backbones proposing a
comprehensive analysis of their intrinsic generalization capabilities, which so
far have been ignored by the research community. We evaluate a wide variety of
feature extractors, from standard residual solutions to transformer-based
architectures, finding an evident linear correlation between large-scale
single-domain classification accuracy and DG capability. Our extensive
experimentation shows that by adopting competitive backbones in conjunction
with effective data augmentation, plain ERM outperforms recent DG solutions and
achieves state-of-the-art accuracy. Moreover, our additional qualitative
studies reveal that novel backbones give more similar representations to
same-class samples, separating different domains in the feature space. This
boost in generalization capabilities leaves marginal room for DG algorithms. It
suggests a new paradigm for investigating the problem, placing backbones in the
spotlight and encouraging the development of consistent algorithms on top of
them. The code is available at https://github.com/PIC4SeR/Back-to-Bones.
Related papers
- Disentangling Masked Autoencoders for Unsupervised Domain Generalization [57.56744870106124]
Unsupervised domain generalization is fast gaining attention but is still far from well-studied.
Disentangled Masked Auto (DisMAE) aims to discover the disentangled representations that faithfully reveal intrinsic features.
DisMAE co-trains the asymmetric dual-branch architecture with semantic and lightweight variation encoders.
arXiv Detail & Related papers (2024-07-10T11:11:36Z) - Back to Basics: A Simple Recipe for Improving Out-of-Domain Retrieval in
Dense Encoders [63.28408887247742]
We study whether training procedures can be improved to yield better generalization capabilities in the resulting models.
We recommend a simple recipe for training dense encoders: Train on MSMARCO with parameter-efficient methods, such as LoRA, and opt for using in-batch negatives unless given well-constructed hard negatives.
arXiv Detail & Related papers (2023-11-16T10:42:58Z) - Towards Reliable Domain Generalization: A New Dataset and Evaluations [45.68339440942477]
We propose a new domain generalization task for handwritten Chinese character recognition (HCCR)
We evaluate eighteen DG methods on the proposed PaHCC dataset and show that the performance of existing methods is still unsatisfactory.
Our dataset and evaluations bring new perspectives to the community for more substantial progress.
arXiv Detail & Related papers (2023-09-12T11:29:12Z) - Improving Generalization with Domain Convex Game [32.07275105040802]
Domain generalization tends to alleviate the poor generalization capability of deep neural networks by learning model with multiple source domains.
A classical solution to DG is domain augmentation, the common belief of which is that diversifying source domains will be conducive to the out-of-distribution generalization.
Our explorations reveal that the correlation between model generalization and the diversity of domains may be not strictly positive, which limits the effectiveness of domain augmentation.
arXiv Detail & Related papers (2023-03-23T14:27:49Z) - When Neural Networks Fail to Generalize? A Model Sensitivity Perspective [82.36758565781153]
Domain generalization (DG) aims to train a model to perform well in unseen domains under different distributions.
This paper considers a more realistic yet more challenging scenario, namely Single Domain Generalization (Single-DG)
We empirically ascertain a property of a model that correlates strongly with its generalization that we coin as "model sensitivity"
We propose a novel strategy of Spectral Adversarial Data Augmentation (SADA) to generate augmented images targeted at the highly sensitive frequencies.
arXiv Detail & Related papers (2022-12-01T20:15:15Z) - On Certifying and Improving Generalization to Unseen Domains [87.00662852876177]
Domain Generalization aims to learn models whose performance remains high on unseen domains encountered at test-time.
It is challenging to evaluate DG algorithms comprehensively using a few benchmark datasets.
We propose a universal certification framework that can efficiently certify the worst-case performance of any DG method.
arXiv Detail & Related papers (2022-06-24T16:29:43Z) - Reappraising Domain Generalization in Neural Networks [8.06370138649329]
Domain generalization (DG) of machine learning algorithms is defined as their ability to learn a domain agnostic hypothesis from multiple training distributions.
We find that a straightforward Empirical Risk Minimization (ERM) baseline consistently outperforms existing DG methods.
We propose a classwise-DG formulation, where for each class, we randomly select one of the domains and keep it aside for testing.
arXiv Detail & Related papers (2021-10-15T10:06:40Z) - COLUMBUS: Automated Discovery of New Multi-Level Features for Domain
Generalization via Knowledge Corruption [12.555885317622131]
We address the challenging domain generalization problem, where a model trained on a set of source domains is expected to generalize well in unseen domains without exposure to their data.
We propose Columbus, a method that enforces new feature discovery via a targeted corruption of the most relevant input and multi-level representations of the data.
arXiv Detail & Related papers (2021-09-09T14:52:05Z) - Semi-Supervised Domain Generalization with Stochastic StyleMatch [90.98288822165482]
In real-world applications, we might have only a few labels available from each source domain due to high annotation cost.
In this work, we investigate semi-supervised domain generalization, a more realistic and practical setting.
Our proposed approach, StyleMatch, is inspired by FixMatch, a state-of-the-art semi-supervised learning method based on pseudo-labeling.
arXiv Detail & Related papers (2021-06-01T16:00:08Z) - Generalizable Person Re-identification with Relevance-aware Mixture of
Experts [45.13716166680772]
We propose a novel method called the relevance-aware mixture of experts (RaMoE)
RaMoE uses an effective voting-based mixture mechanism to dynamically leverage source domains' diverse characteristics to improve the model's generalization.
Considering the target domains' invisibility during training, we propose a novel learning-to-learn algorithm combined with our relation alignment loss to update the voting network.
arXiv Detail & Related papers (2021-05-19T14:19:34Z) - Cross-Domain Facial Expression Recognition: A Unified Evaluation
Benchmark and Adversarial Graph Learning [85.6386289476598]
We develop a novel adversarial graph representation adaptation (AGRA) framework for cross-domain holistic-local feature co-adaptation.
We conduct extensive and fair evaluations on several popular benchmarks and show that the proposed AGRA framework outperforms previous state-of-the-art methods.
arXiv Detail & Related papers (2020-08-03T15:00:31Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.