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

Recent sparse detectors with multiple, e.g. six, decoder layers achievepromising performance but much inference time due to complex heads. Previousworks have explored using dense priors as initialization and builtone-decoder-layer detectors. Although they gain remarkable acceleration, theirperformance still lags behind their six-decoder-layer counterparts by a largemargin. In this work, we aim to bridge this performance gap while retainingfast speed. We find that the architecture discrepancy between dense and sparsedetectors leads to feature conflict, hampering the performance ofone-decoder-layer detectors. Thus we propose Adaptive Sparse Anchor Generator(ASAG) which predicts dynamic anchors on patches rather than grids in a sparseway so that it alleviates the feature conflict problem. For each image, ASAGdynamically selects which feature maps and which locations to predict, forminga fully adaptive way to generate image-specific anchors. Further, a simple andeffective Query Weighting method eases the training instability fromadaptiveness. Extensive experiments show that our method outperformsdense-initialized ones and achieves a better speed-accuracy trade-off. The codeis available at \url{https://github.com/iSEE-Laboratory/ASAG}.

ASAG: Building Strong One-Decoder-Layer Sparse Detectors via Adaptive Sparse Anchor Generation