2023 · 113 citations · 43 references
ComputingComputer ScienceComputer VisionMachine LearningNatural Language ProcessingDeep LearningLanguage ModelingObject DetectionRepresentation LearningRobotic VisionScene UnderstandingCross-domain GeneralizationDomain GeneralizationObject LocalizationRobust LocalizationText ClassificationVisual Object Localization
Single Domain Generalization (SDG) tackles the problem of training a model on a single source domain so that it generalizes to any unseen target domain. While this has been well studied for image classification, the literature on SDG object detection remains almost non-existent. To address the challenges of simultaneously learning robust object localization and representation, we propose to leverage a pre-trained vision-language model to introduce semantic domain concepts via textual prompts. We achieve this via a semantic augmentation strategy acting on the features extracted by the detector backbone, as well as a text-based classification loss. Our experiments evidence the benefits of our approach, outperforming by 10% the only existing SDG object detection method, Single-DGOD [52], on their own diverse weather-driving benchmark.
43
Deep Residual Learning for Image Recognition
Kaiming He, Xiangyu Zhang, Shaoqing Ren et al. · 2016 · 222.1K citations · Full text
Adam: A Method for Stochastic Optimization
Diederik P. Kingma, Jimmy Ba · UvA-DARE (University of Amsterdam) · 2014 · 84.8K citations · Full text
Kaiming He, Georgia Gkioxari, Piotr Dollár et al. · 2017 · 28.8K citations