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

Traditional object detectors employ the dense paradigm of scanning overlocations and scales in an image. The recent query-based object detectors breakthis convention by decoding image features with a set of learnable queries.However, this paradigm still suffers from slow convergence, limitedperformance, and design complexity of extra networks between backbone anddecoder. In this paper, we find that the key to these issues is theadaptability of decoders for casting queries to varying objects. Accordingly,we propose a fast-converging query-based detector, named AdaMixer, by improvingthe adaptability of query-based decoding processes in two aspects. First, eachquery adaptively samples features over space and scales based on estimatedoffsets, which allows AdaMixer to efficiently attend to the coherent regions ofobjects. Then, we dynamically decode these sampled features with an adaptiveMLP-Mixer under the guidance of each query. Thanks to these two criticaldesigns, AdaMixer enjoys architectural simplicity without requiring denseattentional encoders or explicit pyramid networks. On the challenging MS COCObenchmark, AdaMixer with ResNet-50 as the backbone, with 12 training epochs,reaches up to 45.0 AP on the validation set along with 27.9 APs in detectingsmall objects. With the longer training scheme, AdaMixer with ResNeXt-101-DCNand Swin-S reaches 49.5 and 51.3 AP. Our work sheds light on a simple,accurate, and fast converging architecture for query-based object detectors.The code is made available at https://github.com/MCG-NJU/AdaMixer

AdaMixer: A Fast-Converging Query-Based Object Detector