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。
| 説明可能な物体検出× | インスタンスセグメンテーション× | |
|---|---|---|
| 分野 | 深層学習 | 深層学習 |
| 系統 | Machine learning | Machine learning |
| 提唱年≠ | 2016–2017 | 2017 |
| 提唱者≠ | Selvaraju et al. (Grad-CAM); Ribeiro et al. (LIME); Lundberg & Lee (SHAP) | He, K., Gkioxari, G., Dollar, P., Girshick, R. |
| 種類≠ | Post-hoc explainability applied to object detection | Pixel-level detection and mask prediction |
| 原典≠ | Selvaraju, R. R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., & Batra, D. (2017). Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization. Proceedings of the IEEE International Conference on Computer Vision (ICCV), 618–626. DOI ↗ | He, K., Gkioxari, G., Dollar, P., & Girshick, R. (2017). Mask R-CNN. Proceedings of the IEEE International Conference on Computer Vision (ICCV), 2961–2969. DOI ↗ |
| 別名 | XAI Object Detection, Interpretable Object Detection, Transparent Object Detection, Explainable OD | instance-level segmentation, object instance segmentation, mask prediction, panoptic instance segmentation |
| 関連≠ | 5 | 4 |
| 概要≠ | Explainable object detection combines a deep-learning object detector — such as YOLO, Faster R-CNN, or DETR — with post-hoc or built-in explainability methods (Grad-CAM, LIME, SHAP, D-RISE) that visualize why the model placed a bounding box at a particular location and assigned a particular class label, making its decisions auditable by humans. | Instance segmentation is a computer vision task that simultaneously detects every distinct object in an image and produces a precise pixel-level mask for each individual object instance. Unlike semantic segmentation, which labels every pixel with a class, instance segmentation distinguishes between separate objects of the same class, enabling fine-grained spatial understanding. |
| ScholarGateデータセット ↗ |
|
|