Cross-Domain Ensemble Distillation for Domain Generalization
- URL: http://arxiv.org/abs/2211.14058v1
- Date: Fri, 25 Nov 2022 12:32:36 GMT
- Title: Cross-Domain Ensemble Distillation for Domain Generalization
- Authors: Kyungmoon Lee, Sungyeon Kim, Suha Kwak
- Abstract summary: We propose a simple yet effective method for domain generalization, named cross-domain ensemble distillation (XDED)
Our method generates an ensemble of the output logits from training data with the same label but from different domains and then penalizes each output for the mismatch with the ensemble.
We show that models learned by our method are robust against adversarial attacks and image corruptions.
- Score: 17.575016642108253
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Domain generalization is the task of learning models that generalize to
unseen target domains. We propose a simple yet effective method for domain
generalization, named cross-domain ensemble distillation (XDED), that learns
domain-invariant features while encouraging the model to converge to flat
minima, which recently turned out to be a sufficient condition for domain
generalization. To this end, our method generates an ensemble of the output
logits from training data with the same label but from different domains and
then penalizes each output for the mismatch with the ensemble. Also, we present
a de-stylization technique that standardizes features to encourage the model to
produce style-consistent predictions even in an arbitrary target domain. Our
method greatly improves generalization capability in public benchmarks for
cross-domain image classification, cross-dataset person re-ID, and
cross-dataset semantic segmentation. Moreover, we show that models learned by
our method are robust against adversarial attacks and image corruptions.
Related papers
- Generalize or Detect? Towards Robust Semantic Segmentation Under Multiple Distribution Shifts [56.57141696245328]
In open-world scenarios, where both novel classes and domains may exist, an ideal segmentation model should detect anomaly classes for safety.
Existing methods often struggle to distinguish between domain-level and semantic-level distribution shifts.
arXiv Detail & Related papers (2024-11-06T11:03:02Z) - Domain Generalization via Selective Consistency Regularization for Time
Series Classification [16.338176636365752]
Domain generalization methods aim to learn models robust to domain shift with data from a limited number of source domains.
We propose a novel representation learning methodology that selectively enforces prediction consistency between source domains.
arXiv Detail & Related papers (2022-06-16T01:57:35Z) - Adaptive Methods for Aggregated Domain Generalization [26.215904177457997]
In many settings, privacy concerns prohibit obtaining domain labels for the training data samples.
We propose a domain-adaptive approach to this problem, which operates in two steps.
Our approach achieves state-of-the-art performance on a variety of domain generalization benchmarks without using domain labels.
arXiv Detail & Related papers (2021-12-09T08:57:01Z) - Context-Conditional Adaptation for Recognizing Unseen Classes in Unseen
Domains [48.17225008334873]
We propose a feature generative framework integrated with a COntext COnditional Adaptive (COCOA) Batch-Normalization.
The generated visual features better capture the underlying data distribution enabling us to generalize to unseen classes and domains at test-time.
We thoroughly evaluate and analyse our approach on established large-scale benchmark - DomainNet.
arXiv Detail & Related papers (2021-07-15T17:51:16Z) - Adaptive Domain-Specific Normalization for Generalizable Person
Re-Identification [81.30327016286009]
We propose a novel adaptive domain-specific normalization approach (AdsNorm) for generalizable person Re-ID.
In this work, we propose a novel adaptive domain-specific normalization approach (AdsNorm) for generalizable person Re-ID.
arXiv Detail & Related papers (2021-05-07T02:54:55Z) - Generalizable Representation Learning for Mixture Domain Face
Anti-Spoofing [53.82826073959756]
Face anti-spoofing approach based on domain generalization(DG) has drawn growing attention due to its robustness forunseen scenarios.
We propose domain dy-namic adjustment meta-learning (D2AM) without using do-main labels.
To overcome the limitation, we propose domain dy-namic adjustment meta-learning (D2AM) without using do-main labels.
arXiv Detail & Related papers (2021-05-06T06:04:59Z) - Domain Invariant Representation Learning with Domain Density
Transformations [30.29600757980369]
Domain generalization refers to the problem where we aim to train a model on data from a set of source domains so that the model can generalize to unseen target domains.
We show how to use generative adversarial networks to learn such domain transformations to implement our method in practice.
arXiv Detail & Related papers (2021-02-09T19:25:32Z) - Cluster, Split, Fuse, and Update: Meta-Learning for Open Compound Domain
Adaptive Semantic Segmentation [102.42638795864178]
We propose a principled meta-learning based approach to OCDA for semantic segmentation.
We cluster target domain into multiple sub-target domains by image styles, extracted in an unsupervised manner.
A meta-learner is thereafter deployed to learn to fuse sub-target domain-specific predictions, conditioned upon the style code.
We learn to online update the model by model-agnostic meta-learning (MAML) algorithm, thus to further improve generalization.
arXiv Detail & Related papers (2020-12-15T13:21:54Z) - Batch Normalization Embeddings for Deep Domain Generalization [50.51405390150066]
Domain generalization aims at training machine learning models to perform robustly across different and unseen domains.
We show a significant increase in classification accuracy over current state-of-the-art techniques on popular domain generalization benchmarks.
arXiv Detail & Related papers (2020-11-25T12:02:57Z)
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.