Attention Consistency on Visual Corruptions for Single-Source Domain Generalization

Cugu, Ilke; Mancini, Massimiliano; Chen, Yanbei; Akata, Zeynep

doi:10.1109/cvprw56347.2022.00461

Cited by 14 publications

(2 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One intuitive approach to tackle this issue was to diversify the training data distribution by incorporating various environments during the classification process [6,14]. In the field of computer vision, there existed numerous related research works [8,33,39,40,50] that tailored the environment based on image data characteristics (e.g. background and color).…”

Section: Related Workmentioning

confidence: 99%

Cooperative Classification and Rationalization for Graph Generalization

Yue,

Liu,

Liu

et al. 2024

Proceedings of the ACM Web Conference 2024

View full text Add to dashboard Cite

Graph Neural Networks (GNNs) have achieved impressive results in graph classification tasks, but they struggle to generalize effectively when faced with out-of-distribution (OOD) data. Several approaches have been proposed to address this problem. Among them, one solution is to diversify training distributions in vanilla classification by modifying the data environment, yet accessing the environment information is complex. Besides, another promising approach involves rationalization, extracting invariant rationales for predictions. However, extracting rationales is difficult due to limited learning signals, resulting in less accurate rationales and diminished predictions. To address these challenges, in this paper, we propose a Cooperative Classification and Rationalization (C2R) method, consisting of the classification and the rationalization module. Specifically, we first assume that multiple environments are available in the classification module. Then, we introduce diverse training distributions using an environment-conditional generative network, enabling robust graph representations. Meanwhile, the rationalization module employs a separator to identify relevant rationale subgraphs while the remaining non-rationale subgraphs are de-correlated with labels. Next, we align graph representations from the classification module with rationale subgraph representations using the knowledge distillation methods, enhancing the

show abstract

Section: Related Workmentioning

confidence: 99%

Cooperative Classification and Rationalization for Graph Generalization

Yue,

Liu,

Liu

et al. 2024

Proceedings of the ACM Web Conference 2024

View full text Add to dashboard Cite

show abstract

“…We compared our methods AdvST and AdvST-ME with ADA, ME-ADA, MixUp (Zhang et al 2018) (Wang et al 2021). We also included ACVC (Cugu et al 2022), which applies attention consistency to learning from augmented samples.…”

Section: Comparison On Pacsmentioning

confidence: 99%

AdvST: Revisiting Data Augmentations for Single Domain Generalization

Zheng,

Huai,

Zhang

2024

AAAI

View full text Add to dashboard Cite

Single domain generalization (SDG) aims to train a robust model against unknown target domain shifts using data from a single source domain. Data augmentation has been proven an effective approach to SDG. However, the utility of standard augmentations, such as translate, or invert, has not been fully exploited in SDG; practically, these augmentations are used as a part of a data preprocessing procedure. Although it is intuitive to use many such augmentations to boost the robustness of a model to out-of-distribution domain shifts, we lack a principled approach to harvest the benefit brought from multiple these augmentations. Here, we conceptualize standard data augmentations with learnable parameters as semantics transformations that can manipulate certain semantics of a sample, such as the geometry or color of an image. Then, we propose Adversarial learning with Semantics Transformations (AdvST) that augments the source domain data with semantics transformations and learns a robust model with the augmented data. We theoretically show that AdvST essentially optimizes a distributionally robust optimization objective defined on a set of semantics distributions induced by the parameters of semantics transformations. We demonstrate that AdvST can produce samples that expand the coverage on target domain data. Compared with the state-of-the-art methods, AdvST, despite being a simple method, is surprisingly competitive and achieves the best average SDG performance on the Digits, PACS, and DomainNet datasets. Our code is available at https://github.com/gtzheng/AdvST.

show abstract

Single-domain incremental generation network for machinery intelligent fault diagnosis under unknown working speeds

Pu,

Tang,

et al. 2024

Advanced Engineering Informatics

View full text Add to dashboard Cite

Attention Consistency on Visual Corruptions for Single-Source Domain Generalization

Cited by 14 publications

References 26 publications

Cooperative Classification and Rationalization for Graph Generalization

Cooperative Classification and Rationalization for Graph Generalization

AdvST: Revisiting Data Augmentations for Single Domain Generalization

Single-domain incremental generation network for machinery intelligent fault diagnosis under unknown working speeds

Contact Info

Product

Resources

About