Interpreting CLIP's Image Representation via Text-Based Decomposition

Y Gandelsman, AA Efros, J Steinhardt - arXiv preprint arXiv:2310.05916, 2023 - arxiv.org
We investigate the CLIP image encoder by analyzing how individual model components
affect the final representation. We decompose the image representation as a sum across …
被引用次数：28 相关文章

Interpreting CLIP's Image Representation via Text-Based Decomposition

Y Gandelsman, AA Efros, J Steinhardt - arXiv e-prints, 2023 - ui.adsabs.harvard.edu
We investigate the CLIP image encoder by analyzing how individual model components
affect the final representation. We decompose the image representation as a sum across …

Interpreting CLIP's Image Representation via Text-Based Decomposition

Y Gandelsman, AA Efros, J Steinhardt - The Twelfth International … - openreview.net
We investigate the CLIP image encoder by analyzing how individual model components
affect the final representation. We decompose the image representation as a sum across …