방법 비교
선택한 방법을 나란히 검토하세요. 서로 다른 행은 강조 표시됩니다.
| 약지도 객체 탐지× | Vision Transformer× | |
|---|---|---|
| 분야 | 딥러닝 | 딥러닝 |
| 계열 | Machine learning | Machine learning |
| 기원 연도≠ | 2016 (deep WSOD); MIL roots circa 1997 | 2021 |
| 창시자≠ | Bilen, H. & Vedaldi, A. (WSDDN); Multiple Instance Learning origins: Dietterich et al. (1997) | Dosovitskiy, A. et al. |
| 유형≠ | Weakly supervised detection paradigm | Transformer architecture for images (self-attention over patches) |
| 원전≠ | 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 ↗ | Dosovitskiy, A. et al. (2021). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. ICLR. link ↗ |
| 별칭 | WSOD, weakly-supervised detection, image-level supervised detection, multiple instance detection | Görsel Transformer (ViT), görsel transformer, ViT, patch transformer for images |
| 관련 | 5 | 5 |
| 요약≠ | 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. | The Vision Transformer (ViT), introduced by Dosovitskiy and colleagues in 2021, splits an image into fixed-size patches, treats those patches as a sequence, and applies the Transformer self-attention mechanism to image classification. Given enough training data, it surpasses convolutional neural networks (CNNs). |
| ScholarGate데이터셋 ↗ |
|
|