Memory-efficient finetuning

Dr2Net: Dynamic Reversible Dual-Residual Networks for Memory-Efficient Finetuning
Large pretrained models are increasingly crucial in modern computer vision tasks. These models are typically used in downstream tasks …
Chen Zhao, Shuming Liu, Karttikeya Mangalam, Guocheng Qian, Fatimah Zohra, Abdulmohsen Alghannam, Jitendra Malik, Bernard Ghanem
PDF Cite
Dr2Net: Dynamic Reversible Dual-Residual Networks for Memory-Efficient Finetuning
End-to-End Temporal Action Detection with 1B Parameters Across 1000 Frames
Recently, temporal action detection (TAD) has seen significant performance improvement with end-to-end training. However, due to the …
Shuming Liu, Chen-Lin Zhang, Chen Zhao, Bernard Ghanem
PDF Cite
End-to-End Temporal Action Detection with 1B Parameters Across 1000 Frames