uCAP: an unsupervised prompting method for vision-language models
This paper addresses a significant limitation that prevents Contrastive Language-Image Pretrained Models (CLIP) from achieving optimal performance on downstream image classification tasks. The key problem with CLIP-style zero-shot classification is that it requires domain-specific context in the for...
Príomhchruthaitheoirí: | Nguyen, AT, Tai, KS, Chen, BC, Shukla, SN, Yu, H, Torr, P, Tian, TP, Lim, SN |
---|---|
Formáid: | Conference item |
Teanga: | English |
Foilsithe / Cruthaithe: |
Springer
2024
|
Míreanna comhchosúla
Míreanna comhchosúla
-
Berat ucap terima kasih
de réir: Berita Harian , Noor Mohamad Shakil Hameed
Foilsithe / Cruthaithe: (2012) -
NAIB CANSELOR UCAP TAHNIAH DAN PENGHARGAAN
de réir: MPRC, Pusat Media & Perhubungan Awam
Foilsithe / Cruthaithe: (2016) -
PM ucap tahniah kepada lima universiti
de réir: Utusan Malaysia,
Foilsithe / Cruthaithe: (2014) -
An image is worth 1000 lies: adversarial transferability across prompts on vision-language models
de réir: Luo, H, et al.
Foilsithe / Cruthaithe: (2024) -
Ucap perdana I : 20 tahun bersama Mahathir /
de réir: Musa Hitam, Tan Sri, 1934- author
Foilsithe / Cruthaithe: (2007)