Methoden vergleichen

	Schwach überwachte Objektdetektion	Vision Transformer
Fachgebiet	Deep Learning	Deep Learning
Familie	Machine learning	Machine learning
Entstehungsjahr	2016 (deep WSOD); MIL roots circa 1997	2021
Urheber	Bilen, H. & Vedaldi, A. (WSDDN); Multiple Instance Learning origins: Dietterich et al. (1997)	Dosovitskiy, A. et al.
Typ	Weakly supervised detection paradigm	Transformer architecture for images (self-attention over patches)
Wegweisende Quelle	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.	Dosovitskiy, A. et al. (2021). An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. ICLR.
Aliasnamen	WSOD, weakly-supervised detection, image-level supervised detection, multiple instance detection	Görsel Transformer (ViT), görsel transformer, ViT, patch transformer for images
Verwandt	5	5
Zusammenfassung	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).