Mixup Regularization for Region Proposal based Object Detectors
Mixup - a neural network regularization technique based on linear interpolation of labeled sample pairs - has stood out by its capacity to improve model's robustness and generalizability through a surprisingly simple formalism. However, its extension to the field of object detection remains unclear as the interpolation of bounding boxes cannot be naively defined. In this paper, we propose to leverage the inherent region mapping structure of anchors to introduce a mixup-driven training regularization for region proposal based object detectors. The proposed method is benchmarked on standard datasets with challenging detection settings. Our experiments show an enhanced robustness to image alterations along with an ability to decontextualize detections, resulting in an improved generalization power.
Code (0)
등록된 구현이 없습니다.
Tasks
Objectobject-detectionObject DetectionRegion ProposalSimilar Papers 제목 키워드 기반
Object Detection based on Region Decomposition and Assembly
Region-based object detection infers object regions for one or more categories in an image. Due to the recent advances in deep learning and region proposal methods, object detectors based on convolutional neural networks…
Objectobject-detectionObject DetectionRegion ProposalRepGN:Object Detection with Relational Proposal Graph Network
Region based object detectors achieve the state-of-the-art performance, but few consider to model the relation of proposals. In this paper, we explore the idea of modeling the relationships among the proposals for object…
General ClassificationGraph LearningObjectobject-detection+2Mixup-CAM: Weakly-supervised Semantic Segmentation via Uncertainty Regularization
Obtaining object response maps is one important step to achieve weakly-supervised semantic segmentation using image-level labels. However, existing methods rely on the classification task, which could result in a respons…
ClassificationData AugmentationGeneral ClassificationObject+3Collaborative Training between Region Proposal Localization and Classification for Domain Adaptive Object Detection
Object detectors are usually trained with large amount of labeled data, which is expensive and labor-intensive. Pre-trained detectors applied to unlabeled dataset always suffer from the difference of dataset distribution…
Domain AdaptationGeneral ClassificationObjectobject-detection+2Event Camera as Region Proposal Network
The human eye consists of two types of photoreceptors, rods and cones. Rods are responsible for monochrome vision, and cones for color vision. The number of rods is much higher than the cones, which means that most human…
Region Proposal