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 Plus annual

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

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Collecting and annotating images with pixel-wise labels is time-consuming andlaborious. In contrast, synthetic data can be freely available using agenerative model (e.g., DALL-E, Stable Diffusion). In this paper, we show thatit is possible to automatically obtain accurate semantic masks of syntheticimages generated by the Off-the-shelf Stable Diffusion model, which uses onlytext-image pairs during training. Our approach, called DiffuMask, exploits thepotential of the cross-attention map between text and image, which is naturaland seamless to extend the text-driven image synthesis to semantic maskgeneration. DiffuMask uses text-guided cross-attention information to localizeclass/word-specific regions, which are combined with practical techniques tocreate a novel high-resolution and class-discriminative pixel-wise mask. Themethods help to reduce data collection and annotation costs obviously.Experiments demonstrate that the existing segmentation methods trained onsynthetic data of DiffuMask can achieve a competitive performance over thecounterpart of real data (VOC 2012, Cityscapes). For some classes (e.g., bird),DiffuMask presents promising performance, close to the stateof-the-art resultof real data (within 3% mIoU gap). Moreover, in the open-vocabularysegmentation (zero-shot) setting, DiffuMask achieves a new SOTA result onUnseen class of VOC 2012. The project website can be found athttps://weijiawu.github.io/DiffusionMask/.

DiffuMask: Synthesizing Images with Pixel-level Annotations for Semantic Segmentation Using Diffusion Models