appliedml42
@appliedml42
Reversible Vision Transformers https://arxiv.org/abs/2302.04869v1 https://i.imgur.com/XJlssKp.png
1 reply
0 recast
0 reaction
appliedml42
@appliedml42
A memory efficient architecture design for visual recognition which decouples the GPU memory requirement from the depth of the model. We benchmark extensively across both model sizes and tasks and show up to 15.5x reduced memory footprint at roughly identical model complexity, parameters and accuracy.
1 reply
0 recast
0 reaction
appliedml42
@appliedml42
Reversible Vision Transformers | GPU memory requirement | Vision Transformer | Multiscale Vision Transformers | image classification | object detection | video classification | reduced memory footprint | additional computational burden
0 reply
0 recast
0 reaction
