ScholarGate
アシスタント

手法を比較

選択した手法を並べて確認できます。異なる行はハイライト表示されます。

弱教師あり物体検出×物体検出×
分野深層学習深層学習
系統Machine learningMachine learning
提唱年2016 (deep WSOD); MIL roots circa 19972014–2016
提唱者Bilen, H. & Vedaldi, A. (WSDDN); Multiple Instance Learning origins: Dietterich et al. (1997)Girshick, R. et al. (R-CNN); Redmon, J. et al. (YOLO)
種類Weakly supervised detection paradigmSupervised deep learning (region proposal or single-shot)
原典Bilen, H., & Vedaldi, A. (2016). Weakly supervised deep detection networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2846–2854. DOI ↗Girshick, R., Donahue, J., Darrell, T., & Malik, J. (2014). Rich feature hierarchies for accurate object detection and semantic segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 580–587. DOI ↗
別名WSOD, weakly-supervised detection, image-level supervised detection, multiple instance detectionvisual object detection, image object localization, region-based object detection, bounding-box detection
関連53
概要Weakly Supervised Object Detection (WSOD) trains object detectors using only image-level labels — indicating which object classes appear in an image — without requiring costly bounding-box annotations. Multiple Instance Learning (MIL) formulations allow the model to discover the likely location of each object class from classification signals alone, dramatically reducing annotation cost.Object detection is a computer vision task in which a deep neural network simultaneously locates and classifies every instance of one or more object categories within an image, producing a bounding box and a class label for each detected object. Modern detectors — from the R-CNN family to YOLO and DETR — achieve near-human accuracy at real-time speeds on standard benchmarks.
ScholarGateデータセット
  1. v1
  2. 2 出典
  3. PUBLISHED
  1. v1
  2. 2 出典
  3. PUBLISHED

検索へ スライドをダウンロード

ScholarGate手法を比較: Weakly Supervised Object Detection · Object Detection. 2026-06-15に以下より取得 https://scholargate.app/ja/compare