"How structured are the representations in transformer-based vision ..."

Tarun Khajuria, Braian Olmiro Dias, Jaan Aru (2024)

> Home

Details and statistics

DOI: 10.48550/ARXIV.2406.09067

access: open

type: Informal or Other Publication

metadata version: 2024-07-09

- view
  - electronic edition via DOI (open access)
  authority control:
- export record
  dblp key:
  - journals/corr/abs-2406-09067
- ask others
- share record
  persistent URL:
  - https://dblp.org/rec/journals/corr/abs-2406-09067
Tarun Khajuria, Braian Olmiro Dias, Jaan Aru:
How structured are the representations in transformer-based vision encoders? An analysis of multi-object representations in vision-language models. CoRR abs/2406.09067 (2024)

manage site settings

To protect your privacy, all features that rely on external API calls from your browser are turned off by default. You need to opt-in for them to become active. All settings here will be stored as cookies with your web browser. For more information see our F.A.Q.