Papers › Progressive Random Convolutions for Single Domain Generalization

Progressive Random Convolutions for Single Domain Generalization

2 Apr 2023CVPR 2023 1arXiv:2304.00424archive 2025-07-28

Seokeon Choi, Debasmit Das, Sungha Choi, Seunghan Yang, Hyunsin Park, Sungrack Yun

Single domain generalization aims to train a generalizable model with only one source domain to perform well on arbitrary unseen target domains. Image augmentation based on Random Convolutions (RandConv), consisting of one convolution layer randomly initialized for each mini-batch, enables the model to learn generalizable visual representations by distorting local textures despite its simple and lightweight structure. However, RandConv has structural limitations in that the generated image easily loses semantics as the kernel size increases, and lacks the inherent diversity of a single convolution operation. To solve the problem, we propose a Progressive Random Convolution (Pro-RandConv) method that recursively stacks random convolution layers with a small kernel size instead of increasing the kernel size. This progressive approach can not only mitigate semantic distortions by reducing the influence of pixels away from the center in the theoretical receptive field, but also create more effective virtual domains by gradually increasing the style diversity. In addition, we develop a basic random convolution layer into a random convolution block including deformable offsets and affine transformation to support texture and contrast diversification, both of which are also randomly initialized. Without complex generators or adversarial learning, we demonstrate that our simple yet effective augmentation strategy outperforms state-of-the-art methods on single domain generalization benchmarks.

PaperPDFConference PDF

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

DiversityDomain GeneralizationImage AugmentationImage to sketch recognitionPhoto to Rest GeneralizationSingle-Source Domain Generalization

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Photo to Rest Generalization PACS ProRandConv (ResNet18) Accuracy 62.89 #2 of 8 Archive leaderboard report
Single-Source Domain Generalization Digits-five ProRandConv (LeNet) Accuracy 81.35 #2 of 7 Archive leaderboard report
Single-Source Domain Generalization PACS ProRandConv (ResNet18) Accuracy 68.88 #3 of 10 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Convolution

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections