Deep Domain Generalization with Feature-norm Network
Not on the map. Why?
Abstract (arXiv)
In this paper, we tackle the problem of training with multiple source domains with the aim to generalize to new domains at test time without an adaptation step. This is known as domain generalization (DG). Previous works on DG assume identical categories or label space across the source domains. In the case of category shift among the source domains, previous methods on DG are vulnerable to negative transfer due to the large mismatch among label spaces, decreasing the target classification accuracy. To tackle the aforementioned problem, we introduce an end-to-end feature-norm network (FNN) which is robust to negative transfer as it does not need to match the feature distribution among the source domains. We also introduce a collaborative feature-norm network (CFNN) to further improve the generalization capability of FNN. The CFNN matches the predictions of the next most likely categories for each training sample which increases each network's posterior entropy. We apply the proposed FNN and CFNN networks to the problem of DG for image classification tasks and demonstrate significant improvement over the state-of-the-art.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 33 of its 51 references that are in the map. First posted on arXiv 28 Apr 2021.
Builds on
33 of 51 references.
References · 33
- 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,906
- 2017Deep Hashing Network for Unsupervised Domain Adaptationcited by 1,181
- 2017Deeper, Broader and Artier Domain Generalizationcited by 983
- 2017Learning to Generalize: Meta-Learning for Domain Generalizationcited by 762
- 2013Domain Generalization via Invariant Feature Representationcited by 622
- 2017Deep Mutual Learningcited by 621
- 2019Domain Generalization by Solving Jigsaw Puzzlescited by 449
- 2019Domain Generalization via Model-Agnostic Learning of Semantic Featurescited by 405
- 2016Entropy-SGD: Biasing Gradient Descent Into Wide Valleyscited by 357
- 2016Domain Separation Networkscited by 317
- 2020Learning to Generate Novel Domains for Domain Generalizationcited by 296
- 2020Learning to Learn Single Domain Generalizationcited by 295
21 more
- 2015Domain Generalization for Object Recognition with Multi-task Autoencoderscited by 253
- 2019Episodic Training for Domain Generalizationcited by 245
- 2017NormFace: L2 Hypersphere Embedding for Face Verificationcited by 237
- 2020Domain Generalization using Causal Matchingcited by 224
- 2020Cross-Domain Few-Shot Classification via Learned Feature-Wise Transformationcited by 183
- 2019Domain Generalization Using a Mixture of Multiple Latent Domainscited by 170
- 2018Open Set Domain Adaptation by Backpropagationcited by 150
- 2018Domain Generalization via Conditional Invariant Representationcited by 146
- 2019Feature-Critic Networks for Heterogeneous Domain Generalizationcited by 130
- 2018Partial Adversarial Domain Adaptationcited by 127
- 2020Learning from Extrinsic and Intrinsic Supervisions for Domain Generalizationcited by 108
- 2020Learning to Learn with Variational Information Bottleneck for Domain Generalizationcited by 102
- 2015Scatter Component Analysis: A Unified Framework for Domain Adaptation and Domain Generalizationcited by 96
- 2017L2-constrained Softmax Loss for Discriminative Face Verificationcited by 96
- 2017Partial Transfer Learning with Selective Adversarial Networkscited by 84
- 2019Correlation-aware Adversarial Domain Adaptation and Generalizationcited by 65
- 2020Adversarial-Learned Loss for Domain Adaptationcited by 65
- 2020Unsupervised Multi-Class Domain Adaptation: Theory, Algorithms, and Practicecited by 43
- 2018Multi-component Image Translation for Deep Domain Generalizationcited by 40
- 2018Ring loss: Convex Feature Normalization for Face Recognitioncited by 39
- 2019On Minimum Discrepancy Estimation for Deep Domain Adaptationcited by 34
Built on by
Citing papers per year: 2021: 1; 2022: 1; 2023: 0; 2024: 1.
3 papers.