Domain Adaptation for Object Detection using SE Adaptors and Center Loss
Despite growing interest in object detection, very few works address the extremely practical problem of cross-domain robustness especially for automative applications. In order to prevent drops in performance due to domain shift, we introduce an unsupervised domain adaptation method built on the foundation of faster-RCNN with two domain adaptation components addressing the shift at the instance and image levels respectively and apply a consistency regularization between them. We also introduce a family of adaptation layers that leverage the squeeze excitation mechanism called SE Adaptors to improve domain attention and thus improves performance without any prior requirement of knowledge of the new target domain. Finally, we incorporate a center loss in the instance and image level representations to improve the intra-class variance. We report all results with Cityscapes as our source domain and Foggy Cityscapes as the target domain outperforming previous baselines.
Code (1)
Tasks
Domain Adaptationobject-detectionObject DetectionUnsupervised Domain AdaptationSimilar Papers 제목 키워드 기반
FoRA: Low-Rank Adaptation Model beyond Multimodal Siamese Network
Multimodal object detection offers a promising prospect to facilitate robust detection in various visual conditions. However, existing two-stream backbone networks are challenged by complex fusion and substantial paramet…
Objectobject-detectionObject DetectionStyle-Guided Domain Adaptation for Face Presentation Attack Detection
Domain adaptation (DA) or domain generalization (DG) for face presentation attack detection (PAD) has attracted attention recently with its robustness against unseen attack scenarios. Existing DA/DG-based PAD methods, ho…
Domain AdaptationDomain GeneralizationFace Presentation Attack DetectionMeta-LearningEfficient Model Adaptation for Continual Learning at the Edge
Most machine learning (ML) systems assume stationary and matching data distributions during training and deployment. This is often a false assumption. When ML models are deployed on real devices, data distributions often…
AutoMLContinual LearningDomain AdaptationNeural Architecture SearchUnsupervised Domain Adaptation from Synthetic to Real Images for Anchorless Object Detection
Synthetic images are one of the most promising solutions to avoid high costs associated with generating annotated datasets to train supervised convolutional neural networks (CNN). However, to allow networks to generalize…
Domain AdaptationObjectobject-detectionObject Detection+1Self domain adapted network
Domain shift is a major problem for deploying deep networks in clinical practice. Network performance drops significantly with (target) images obtained differently than its (source) training data. Due to a lack of target…
Domain AdaptationSelf-Supervised LearningUnsupervised Domain Adaptation