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/

Zendy Plus

Presents the access of premium content as premium feature

Premium Content

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

Zendy Tools

Zendy Open

Large, pre-trained generative models have been increasingly popular anduseful to both the research and wider communities. Specifically, BigGANs aclass-conditional Generative Adversarial Networks trained onImageNet---achieved excellent, state-of-the-art capability in generatingrealistic photos. However, fine-tuning or training BigGANs from scratch ispractically impossible for most researchers and engineers because (1) GANtraining is often unstable and suffering from mode-collapse; and (2) thetraining requires a significant amount of computation, 256 Google TPUs for 2days or 8xV100 GPUs for 15 days. Importantly, many pre-trained generativemodels both in NLP and image domains were found to contain biases that areharmful to society. Thus, we need computationally-feasible methods formodifying and re-purposing these huge, pre-trained models for downstream tasks.In this paper, we propose a cost-effective optimization method for improvingand re-purposing BigGANs by fine-tuning only the class-embedding layer. We showthe effectiveness of our model-editing approach in three tasks: (1)significantly improving the realism and diversity of samples of completemode-collapse classes; (2) re-purposing ImageNet BigGANs for generating imagesfor Places365; and (3) de-biasing or improving the sample diversity forselected ImageNet classes.

A cost-effective method for improving and re-purposing large, pre-trained GANs by fine-tuning their class-embeddings