English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Existing image augmentation methods consist of two categories:perturbation-based methods and generative methods. Perturbation-based methodsapply pre-defined perturbations to augment an original image, but only locallyvary the image, thus lacking image diversity. In contrast, generative methodsbring more image diversity in the augmented images but may not preservesemantic consistency, thus incorrectly changing the essential semantics of theoriginal image. To balance image diversity and semantic consistency inaugmented images, we propose SGID, a Semantic-guided Generative Imageaugmentation method with Diffusion models for image classification.Specifically, SGID employs diffusion models to generate augmented images withgood image diversity. More importantly, SGID takes image labels and captions asguidance to maintain semantic consistency between the augmented and originalimages. Experimental results show that SGID outperforms the best augmentationbaseline by 1.72% on ResNet-50 (from scratch), 0.33% on ViT (ImageNet-21k), and0.14% on CLIP-ViT (LAION-2B). Moreover, SGID can be combined with other imageaugmentation baselines and further improves the overall performance. Wedemonstrate the semantic consistency and image diversity of SGID throughquantitative human and automated evaluations, as well as qualitative casestudies.

Semantic-Guided Generative Image Augmentation Method with Diffusion Models for Image Classification