Sparse Generation: Making Pseudo Labels Sparse for Point Weakly Supervised Object Detection on Low Data Volume
Existing pseudo label generation methods for point weakly supervised object detection are inadequate in low data volume and dense object detection tasks. We consider the generation of weakly supervised pseudo labels as the model's sparse output, and propose Sparse Generation as a solution to make pseudo labels sparse. The method employs three processing stages (Mapping, Mask, Regression), constructs dense tensors through the relationship between data and detector model, optimizes three of its parameters, and obtains a sparse tensor, thereby indirectly obtaining higher quality pseudo labels, and addresses the model's density problem on low data volume. Additionally, we propose perspective-based matching, which provides more rational pseudo boxes for prediction missed on instances. In comparison to the SOTA method, on four datasets (MS COCO-val, RSOD, SIMD, Bullet-Hole), the experimental results demonstrated a significant advantage.
Code (1)
Tasks
Dense Object Detectionobject-detectionObject DetectionPseudo LabelWeakly Supervised Object DetectionSimilar Papers 제목 키워드 기반
Multispectral Pedestrian Detection with Sparsely Annotated Label
Although existing Sparsely Annotated Object Detection (SAOD) approches have made progress in handling sparsely annotated environments in multispectral domain, where only some pedestrians are annotated, they still have th…
object-detectionObject DetectionPedestrian DetectionPseudo LabelAugmenting Ground-Level PM2.5 Prediction via Kriging-Based Pseudo-Label Generation
Fusing abundant satellite data with sparse ground measurements constitutes a major challenge in climate modeling. To address this, we propose a strategy to augment the training dataset by introducing unlabeled satellite …
Data AugmentationPseudo LabelSpatial InterpolationBP-SGCN: Behavioral Pseudo-Label Informed Sparse Graph Convolution Network for Pedestrian and Heterogeneous Trajectory Prediction
Trajectory prediction allows better decision-making in applications of autonomous vehicles or surveillance by predicting the short-term future movement of traffic agents. It is classified into pedestrian or heterogeneous…
Autonomous VehiclesPredictionPseudo LabelTrajectory PredictionSparseDet: Improving Sparsely Annotated Object Detection with Pseudo-positive Mining
Training with sparse annotations is known to reduce the performance of object detectors. Previous methods have focused on proxies for missing ground truth annotations in the form of pseudo-labels for unlabeled boxes. We …
object-detectionObject DetectionSelf-Supervised LearningSemi-Supervised Object DetectionCoDTS: Enhancing Sparsely Supervised Collaborative Perception with a Dual Teacher-Student Framework
Current collaborative perception methods often rely on fully annotated datasets, which can be expensive to obtain in practical situations. To reduce annotation costs, some works adopt sparsely supervised learning techniq…