collaborators
Showing cs.CVShow all

6 papers · 1 filter

cs.CV2024

S2HPruner: Soft-to-Hard Distillation Bridges the Discretization Gap in Pruning

Weihao Lin, Shengji Tang, Chong Yu +2

Recently, differentiable mask pruning methods optimize the continuous relaxation architecture (soft network) as the proxy of the pruned discrete network (hard network) for superior…

cs.CV2024

Once for Both: Single Stage of Importance and Sparsity Search for Vision Transformer Compression

Hancheng Ye, Chong Yu, Peng Ye +5

Recent Vision Transformer Compression (VTC) works mainly follow a two-stage scheme, where the importance score of each model unit is first evaluated or preset in each submodule, fo…

cs.CV2024

Enhanced Sparsification via Stimulative Training

Shengji Tang, Weihao Lin, Hancheng Ye +4

Sparsification-based pruning has been an important category in model compression. Existing methods commonly set sparsity-inducing penalty terms to suppress the importance of droppe…

cs.CV2024

MADTP: Multimodal Alignment-Guided Dynamic Token Pruning for Accelerating Vision-Language Transformer

Jianjian Cao, Peng Ye, Shengze Li +4

Vision-Language Transformers (VLTs) have shown great success recently, but are meanwhile accompanied by heavy computation costs, where a major reason can be attributed to the large…

cs.CV2023

Efficient Architecture Search via Bi-level Data Pruning

Chongjun Tu, Peng Ye, Weihao Lin +5

Improving the efficiency of Neural Architecture Search (NAS) is a challenging but significant task that has received much attention. Previous works mainly adopted the Differentiabl…

cs.CV20236 cited

SpVOS: Efficient Video Object Segmentation with Triple Sparse Convolution

Weihao Lin, Tao Chen, Chong Yu

Semi-supervised video object segmentation (Semi-VOS), which requires only annotating the first frame of a video to segment future frames, has received increased attention recently.…