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

Weakly supervised object localization (WSOL) aims to learn object localizersolely by using image-level labels. The convolution neural network (CNN) basedtechniques often result in highlighting the most discriminative part of objectswhile ignoring the entire object extent. Recently, the transformer architecturehas been deployed to WSOL to capture the long-range feature dependencies withself-attention mechanism and multilayer perceptron structure. Nevertheless,transformers lack the locality inductive bias inherent to CNNs and thereforemay deteriorate local feature details in WSOL. In this paper, we propose anovel framework built upon the transformer, termed LCTR (Local ContinuityTRansformer), which targets at enhancing the local perception capability ofglobal features among long-range feature dependencies. To this end, we proposea relational patch-attention module (RPAM), which considers cross-patchinformation on a global basis. We further design a cue digging module (CDM),which utilizes local features to guide the learning trend of the model forhighlighting the weak local responses. Finally, comprehensive experiments arecarried out on two widely used datasets, ie, CUB-200-2011 and ILSVRC, to verifythe effectiveness of our method.

LCTR: On Awakening the Local Continuity of Transformer for Weakly Supervised Object Localization