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

Despite recent attention and exploration of depth for various tasks, it isstill an unexplored modality for weakly-supervised object detection (WSOD). Wepropose an amplifier method for enhancing the performance of WSOD byintegrating depth information. Our approach can be applied to any WSOD methodbased on multiple-instance learning, without necessitating additionalannotations or inducing large computational expenses. Our proposed methodemploys a monocular depth estimation technique to obtain hallucinated depthinformation, which is then incorporated into a Siamese WSOD network usingcontrastive loss and fusion. By analyzing the relationship between languagecontext and depth, we calculate depth priors to identify the bounding boxproposals that may contain an object of interest. These depth priors are thenutilized to update the list of pseudo ground-truth boxes, or adjust theconfidence of per-box predictions. Our proposed method is evaluated on sixdatasets (COCO, PASCAL VOC, Conceptual Captions, Clipart1k, Watercolor2k, andComic2k) by implementing it on top of two state-of-the-art WSOD methods, and wedemonstrate a substantial enhancement in performance.

Boosting Weakly Supervised Object Detection using Fusion and Priors from Hallucinated Depth