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

The emergence of CLIP has opened the way for open-world image perception. Thezero-shot classification capabilities of the model are impressive but areharder to use for dense tasks such as image segmentation. Several methods haveproposed different modifications and learning schemes to produce dense output.Instead, we propose in this work an open-vocabulary semantic segmentationmethod, dubbed CLIP-DIY, which does not require any additional training orannotations, but instead leverages existing unsupervised object localizationapproaches. In particular, CLIP-DIY is a multi-scale approach that directlyexploits CLIP classification abilities on patches of different sizes andaggregates the decision in a single map. We further guide the segmentationusing foreground/background scores obtained using unsupervised objectlocalization methods. With our method, we obtain state-of-the-art zero-shotsemantic segmentation results on PASCAL VOC and perform on par with the bestmethods on COCO. The code is available athttp://github.com/wysoczanska/clip-diy

CLIP-DIY: CLIP Dense Inference Yields Open-Vocabulary Semantic Segmentation For-Free