Perception Encoder: The best visual embeddings are not at the output of the network
Daniel Bolya, Po-Yao Huang, Peize Sun, Jang Hyun Cho, Andrea Madotto, Chen Wei, Tengyu Ma, Jiale Zhi and 10 more
Who it is from
Metaaffiliation declared by the authors, according to OpenAlex
Other papers from the same organizations
- Evaluating Text-to-Visual Generation with Image-to-Text GenerationMeta · 637 citations
- The Open Materials 2024 (OMat24) inorganic materials dataset and modelsMeta · 573 citations
- VRT: A Video Restoration TransformerMeta · 567 citations
- UMA: A Family of Universal Models for AtomsMeta · 531 citations
- Emu Edit: Precise Image Editing via Recognition and Generation TasksMeta · 423 citations
- LLM-Rec: Personalized Recommendation via Prompting Large Language ModelsMeta · 392 citations