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

Object proposal generation is an important and fundamental task in computervision. In this paper, we propose ProposalCLIP, a method towards unsupervisedopen-category object proposal generation. Unlike previous works which require alarge number of bounding box annotations and/or can only generate proposals forlimited object categories, our ProposalCLIP is able to predict proposals for alarge variety of object categories without annotations, by exploiting CLIP(contrastive language-image pre-training) cues. Firstly, we analyze CLIP forunsupervised open-category proposal generation and design an objectness scorebased on our empirical analysis on proposal selection. Secondly, a graph-basedmerging module is proposed to solve the limitations of CLIP cues and mergefragmented proposals. Finally, we present a proposal regression module thatextracts pseudo labels based on CLIP cues and trains a lightweight network tofurther refine proposals. Extensive experiments on PASCAL VOC, COCO and VisualGenome datasets show that our ProposalCLIP can better generate proposals thanprevious state-of-the-art methods. Our ProposalCLIP also shows benefits fordownstream tasks, such as unsupervised object detection.

ProposalCLIP: Unsupervised Open-Category Object Proposal Generation via Exploiting CLIP Cues