Search Results for author:
Found 5 papers, 3 papers with code
PYRA: Parallel Yielding Re-Activation for Training-Inference Efficient Task Adaptation
Consequently, a simple combination of them cannot guarantee accomplishing both training efficiency and inference efficiency with minimal costs.
Re-parameterized Low-rank Prompt: Generalize a Vision-Language Model within 0.5K Parameters
On the other hand, complicated structures and update rules largely increase the computation and storage cost.
Consolidator: Mergeable Adapter with Grouped Connections for Visual Adaptation
To further enhance the model's capacity to transfer knowledge under a constrained storage budget and keep inference efficient, we consolidate the parameters in two stages: 1. between adaptation and storage, and 2. between loading and inference.
Manipulating Identical Filter Redundancy for Efficient Pruning on Deep and Complicated CNN
The existence of redundancy in Convolutional Neural Networks (CNNs) enables us to remove some filters/channels with acceptable performance drops.
ResRep: Lossless CNN Pruning via Decoupling Remembering and Forgetting
Via training with regular SGD on the former but a novel update rule with penalty gradients on the latter, we realize structured sparsity.
