Prismer: A Vision-Language Model with Multi-Task Experts
Abstrak
Recent vision-language models have shown impressive multi-modal generation capabilities. However, typically they require training huge models on massive datasets. As a more scalable alternative, we introduce Prismer, a data- and parameter-efficient vision-language model that leverages an ensemble of task-specific experts. Prismer only requires training of a small number of components, with the majority of network weights inherited from multiple readily-available, pre-trained experts, and kept frozen during training. By leveraging experts from a wide range of domains, we show Prismer can efficiently pool this expert knowledge and adapt it to various vision-language reasoning tasks. In our experiments, we show that Prismer achieves fine-tuned and few-shot learning performance which is competitive with current state-of-the-arts, whilst requiring up to two orders of magnitude less training data. Code is available at https://github.com/NVlabs/prismer.
Topik & Kata Kunci
Penulis (6)
Shikun Liu
Linxi (Jim) Fan
Edward Johns
Zhiding Yu
Chaowei Xiao
Anima Anandkumar
Akses Cepat
PDF tidak tersedia langsung
Cek di sumber asli →- Tahun Terbit
- 2023
- Bahasa
- en
- Total Sitasi
- 33×
- Sumber Database
- Semantic Scholar
- Akses
- Open Access ✓