Semi-Supervised Domain Generalization with Evolving Intermediate Domain
- URL: http://arxiv.org/abs/2111.10221v3
- Date: Wed, 5 Apr 2023 07:28:18 GMT
- Title: Semi-Supervised Domain Generalization with Evolving Intermediate Domain
- Authors: Luojun Lin, Han Xie, Zhishu Sun, Weijie Chen, Wenxi Liu, Yuanlong Yu,
Lei Zhang
- Abstract summary: Domain Generalization aims to generalize a model trained on multiple source domains to an unseen target domain.
We introduce a novel paradigm of DG, termed as Semi-Supervised Domain Generalization.
We develop a pseudo labeling phase and a generalization phase independently for SSDG.
- Score: 24.75184388536862
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Domain Generalization (DG) aims to generalize a model trained on multiple
source domains to an unseen target domain. The source domains always require
precise annotations, which can be cumbersome or even infeasible to obtain in
practice due to the vast amount of data involved. Web data, however, offers an
opportunity to access large amounts of unlabeled data with rich style
information, which can be leveraged to improve DG. From this perspective, we
introduce a novel paradigm of DG, termed as Semi-Supervised Domain
Generalization (SSDG), to explore how the labeled and unlabeled source domains
can interact, and establish two settings, including the close-set and open-set
SSDG. The close-set SSDG is based on existing public DG datasets, while the
open-set SSDG, built on the newly-collected web-crawled datasets, presents a
novel yet realistic challenge that pushes the limits of current technologies. A
natural approach of SSDG is to transfer knowledge from labeled data to
unlabeled data via pseudo labeling, and train the model on both labeled and
pseudo-labeled data for generalization. Since there are conflicting goals
between domain-oriented pseudo labeling and out-of-domain generalization, we
develop a pseudo labeling phase and a generalization phase independently for
SSDG. Unfortunately, due to the large domain gap, the pseudo labels provided in
the pseudo labeling phase inevitably contain noise, which has negative affect
on the subsequent generalization phase. Therefore, to improve the quality of
pseudo labels and further enhance generalizability, we propose a cyclic
learning framework to encourage a positive feedback between these two phases,
utilizing an evolving intermediate domain that bridges the labeled and
unlabeled domains in a curriculum learning manner...
Related papers
- GenGMM: Generalized Gaussian-Mixture-based Domain Adaptation Model for Semantic Segmentation [0.9626666671366837]
We introduce the Generalized Gaussian-mixture-based (GenGMM) domain adaptation model, which harnesses the underlying data distribution in both domains.
Experiments demonstrate the effectiveness of our approach.
arXiv Detail & Related papers (2024-10-21T20:21:09Z) - 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) - Adaptive Betweenness Clustering for Semi-Supervised Domain Adaptation [108.40945109477886]
We propose a novel SSDA approach named Graph-based Adaptive Betweenness Clustering (G-ABC) for achieving categorical domain alignment.
Our method outperforms previous state-of-the-art SSDA approaches, demonstrating the superiority of the proposed G-ABC algorithm.
arXiv Detail & Related papers (2024-01-21T09:57:56Z) - Label-Efficient Domain Generalization via Collaborative Exploration and
Generalization [28.573872986524794]
This paper introduces label-efficient domain generalization (LEDG) to enable model generalization with label-limited source domains.
We propose a novel framework called Collaborative Exploration and Generalization (CEG) which jointly optimize active exploration and semi-supervised generalization.
arXiv Detail & Related papers (2022-08-07T05:34:50Z) - Localized Adversarial Domain Generalization [83.4195658745378]
Adversarial domain generalization is a popular approach to domain generalization.
We propose localized adversarial domain generalization with space compactness maintenance(LADG)
We conduct comprehensive experiments on the Wilds DG benchmark to validate our approach.
arXiv Detail & Related papers (2022-05-09T08:30:31Z) - Compound Domain Generalization via Meta-Knowledge Encoding [55.22920476224671]
We introduce Style-induced Domain-specific Normalization (SDNorm) to re-normalize the multi-modal underlying distributions.
We harness the prototype representations, the centroids of classes, to perform relational modeling in the embedding space.
Experiments on four standard Domain Generalization benchmarks reveal that COMEN exceeds the state-of-the-art performance without the need of domain supervision.
arXiv Detail & Related papers (2022-03-24T11:54:59Z) - Better Pseudo-label: Joint Domain-aware Label and Dual-classifier for
Semi-supervised Domain Generalization [26.255457629490135]
We propose a novel framework via joint domain-aware labels and dual-classifier to produce high-quality pseudo-labels.
To predict accurate pseudo-labels under domain shift, a domain-aware pseudo-labeling module is developed.
Also, considering inconsistent goals between generalization and pseudo-labeling, we employ a dual-classifier to independently perform pseudo-labeling and domain generalization in the training process.
arXiv Detail & Related papers (2021-10-10T15:17:27Z) - Generalize then Adapt: Source-Free Domain Adaptive Semantic Segmentation [78.38321096371106]
Prior arts assume concurrent access to both labeled source and unlabeled target, making them unsuitable for scenarios demanding source-free adaptation.
In this work, we enable source-free DA by partitioning the task into two: a) source-only domain generalization and b) source-free target adaptation.
We introduce a novel conditional prior-enforcing auto-encoder that discourages spatial irregularities, thereby enhancing the pseudo-label quality.
arXiv Detail & Related papers (2021-08-25T14:18:59Z) - Dual Distribution Alignment Network for Generalizable Person
Re-Identification [174.36157174951603]
Domain generalization (DG) serves as a promising solution to handle person Re-Identification (Re-ID)
We present a Dual Distribution Alignment Network (DDAN) which handles this challenge by selectively aligning distributions of multiple source domains.
We evaluate our DDAN on a large-scale Domain Generalization Re-ID (DG Re-ID) benchmark.
arXiv Detail & Related papers (2020-07-27T00:08:07Z)
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.