yossigandelsman/clip_text_span
official implementation of "Interpreting CLIP's Image Representation via Text-Based Decomposition"
Jupyter NotebookMIT
Stargazers
- 2gunsuAgency for Defense Development (ADD)
- aengusng8@VinAIResearch
- AGTSAAA
- Alan-QinHKUST
- ArsenLuca
- CharlieJCJBerkeley, CA
- Cogito2012Meta Reality Labs
- dmarxStability.ai, Eleuther.ai
- enkeejunior1Seoul National University, the department of physics education
- FutureTwT山东省济南市
- harryteaUniversity of Science and Technology of China
- HarveyYi
- hujunchao
- huzeyann
- Jacksonroad
- junha1125KAIST
- Key-lei福建
- lxzcproWestlake University
- machanicTsinghua University
- MartinserNankai University
- menegazzi
- MollyluluSingapore
- pbayliesDurham, NC
- PhilipflygInstitute for AI Industry Research, Tsinghua University
- RuoyuChen10Chinese Academy of Sciences
- SakurajimaMaiii@aiwaves-cn
- SierkinhaneNUS, Tencent
- SorrowElel
- Space-XunNLPR
- verigle
- vishaal27University of Tübingen | University of Cambridge
- YangShiJun-81
- yossigandelsman
- YTEP-ZHI@OpenDriveLab
- yuliangCarmelo
- YuWLong666Tianjin University