Active Sample Selection and Correction Propagation on a Gradually-Augmented Graph
When data have a complex manifold structure or the characteristics of data evolve over time, it is unrealistic to expect a graph-based semi-supervised learning method to achieve flawless classification given a small number of initial annotations. To address this issue with minimal human interventions, we propose (i) a sample selection criterion used for \textit{active} query of informative samples by minimizing the expected prediction error, and (ii) an efficient {\it correction propagation} method that propagates human correction on selected samples over a {\it gradually-augmented graph} to unlabeled samples without rebuilding the affinity graph. Experimental results conducted on three real world datasets validate that our active sample selection and correction propagation algorithm quickly reaches high quality classification results with minimal human interventions.
Code (0)
등록된 구현이 없습니다.
Tasks
General ClassificationSimilar Papers 제목 키워드 기반
Loss-based Sequential Learning for Active Domain Adaptation
Active domain adaptation (ADA) studies have mainly addressed query selection while following existing domain adaptation strategies. However, we argue that it is critical to consider not only query selection criteria but …
DiversityDomain AdaptationInteractive Medical-SAM2 GUI: A Napari-based semi-automatic annotation tool for medical images
Interactive Medical-SAM2 GUI is an open-source desktop application for semi-automatic annotation of 2D and 3D medical images. Built on the Napari multi-dimensional viewer, box/point prompting is integrated with SAM2-styl…
Robust Deep Learning with Active Noise Cancellation for Spatial Computing
This paper proposes CANC, a Co-teaching Active Noise Cancellation method, applied in spatial computing to address deep learning trained with extreme noisy labels. Deep learning algorithms have been successful in spatial …
Deep LearningRetrievalFrom Calibration to Refinement: Seeking Certainty via Probabilistic Evidence Propagation for Noisy-Label Person Re-Identification
With the increasing demand for robust person Re-ID in unconstrained environments, learning from datasets with noisy labels and sparse per-identity samples remains a critical challenge. Existing noise-robust person Re-ID …
Person Re-IdentificationIMPose: Interactive Multi-person Pose Estimation with Dynamic Correction Propagation
High-quality dynamic human pose annotation equips AI with precise motion kinematics to enable human behavior mastery, yet remains labor-intensive and time-consuming. Current annotation tools either lack temporal correcti…
Multi-Person Pose Estimation