Weakly supervised vision transformer
Weakly Supervised Vision Transformer (WS-ViT) trains a Vision Transformer on image data that lacks precise pixel-level annotations, instead using cheaper, noisier supervision such as image-level class tags, bounding boxes, or web-scraped text. The global self-attention mechanism of the transformer makes it especially capable of localising objects and learning discriminative features from these incomplete labels.
Izvorni zapis
Citati kopirani doslovno iz izvornog zapisa metode. Ne impliciraju nikakvu provjeru na razini tvrdnje.
- Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J., & Houlsby, N. (2021). An image is worth 16x16 words: Transformers for image recognition at scale. In International Conference on Learning Representations (ICLR). · URL
- Zhou, Z.-H. (2022). A brief introduction to weakly supervised learning. National Science Review, 5(1), 44–53. · DOI 10.1093/nsr/nwx106
Uređene tvrdnje
Tvrdnje pohranjene u knjigu dokaza, svaka s vlastitom procjenom.
Ovaj prikaz ne izmišlja procjenu tvrdnje kada knjiga dokaza nema nijednu.
Povezane metode
Generirano iz grafa metode i prikazano kao strojno predložene relacije — ne implicira se nikakva tvrdnja dokaza.