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 detection in urban scenarios is crucial for autonomous driving inintelligent traffic systems. However, unlike conventional object detectiontasks, urban-scene images vary greatly in style. For example, images taken onsunny days differ significantly from those taken on rainy days. Therefore,models trained on sunny day images may not generalize well to rainy day images.In this paper, we aim to solve the single-domain generalizable object detectiontask in urban scenarios, meaning that a model trained on images from oneweather condition should be able to perform well on images from any otherweather conditions. To address this challenge, we propose a novel DoubleAUGmentation (DoubleAUG) method that includes image- and feature-levelaugmentation schemes. In the image-level augmentation, we consider thevariation in color information across different weather conditions and proposea Color Perturbation (CP) method that randomly exchanges the RGB channels togenerate various images. In the feature-level augmentation, we propose toutilize a Dual-Style Memory (DSM) to explore the diverse style information onthe entire dataset, further enhancing the model's generalization capability.Extensive experiments demonstrate that our proposed method outperformsstate-of-the-art methods. Furthermore, ablation studies confirm theeffectiveness of each module in our proposed method. Moreover, our method isplug-and-play and can be integrated into existing methods to further improvemodel performance.

DoubleAUG: Single-domain Generalized Object Detector in Urban via Color Perturbation and Dual-style Memory