REVIEW 3 cited by
Robust and Generalizable Visual Representation Learning via Random Convolutions
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
While successful for various computer vision tasks, deep neural networks have shown to be vulnerable to texture style shifts and small perturbations to which humans are robust. In this work, we show that the robustness of neural networks can be greatly improved through the use of random convolutions as data augmentation. Random convolutions are approximately shape-preserving and may distort local textures. Intuitively, randomized convolutions create an infinite number of new domains with similar global shapes but random local textures. Therefore, we explore using outputs of multi-scale random convolutions as new images or mixing them with the original images during training. When applying a network trained with our approach to unseen domains, our method consistently improves the performance on domain generalization benchmarks and is scalable to ImageNet. In particular, in the challenging scenario of generalizing to the sketch domain in PACS and to ImageNet-Sketch, our method outperforms state-of-art methods by a large margin. More interestingly, our method can benefit downstream tasks by providing a more robust pretrained visual representation.
Forward citations
Cited by 3 Pith papers
-
Adversarial Data Augmentation for Single Domain Generalization via Lyapunov Exponent-Guided Optimization
LEAwareSGD modulates the learning rate with a Lyapunov exponent estimate and claims state-of-the-art accuracy on three single-domain generalization benchmarks, but the method is underspecified and its hyperparameters ...
-
ConStyX: Content Style Augmentation for Generalizable Medical Image Segmentation
ConStyX augments deep features in both content and style and re-weights them by similarity and confidence, improving single-domain generalization for optic disc and cup segmentation.
-
Fully Automated SAM for Single-source Domain Generalization in Medical Image Segmentation
FA-SAM automates SAM-based medical segmentation across domains by generating prompt boxes with an uncertainty-enhanced network and fusing image and prompt embeddings.
Discussion (0). Continue with ORCID to comment.