Abstract

Abstract Capitalizing on large pre-trained models for various downstream tasks of interest have recently emerged with promising performance. Due to the ever-growing model size, the standard full fine

Read More

NeurIPS23_ST-Adapter_poster

ST-Adapter: Parameter-Efficient Image-to-Video Transfer Learning Junting Pan*, Ziyi Lin*, Xiatian Zhu, Jing Shao, Hongsheng Li

Read More

NeurIPS23_ST-Adapter_poster

4. Ablation Study on Efficiency The same ViT-B/16 with CLIP pre-training is used for all experiments. Models & source code: https://github /linziyi96/st-adapter

Read More

People also like:

Get In Touch

Connect With Us

📱

South Africa (Sales & Engineering HQ)

+27 10 247 8396

📍

Headquarters & Manufacturing

Unit 7, Summit Place, 21 Summit Rd, Midrand, Johannesburg, 1685, South Africa