☆ 3.8 Proceedings Paper

Vision Transformer Slimming: Multi-Dimension Searching in Continuous Optimization Space

2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022) (2022)

GLiT: Neural Architecture Search for Global and Local Image Transformer

Boyu Chen et al.

Summary: The paper introduces a new Neural Architecture Search (NAS) method to find a better transformer architecture for image recognition. By incorporating a locality module and new search algorithms, the method allows for a trade-off between global and local information, as well as optimizing low-level design choices in each module. Through extensive experiments on the ImageNet dataset, the method demonstrates the ability to find more efficient and discriminative transformer variants compared to existing models like ResNet101 and ViT.

2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021) (2021)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

BN-NAS: Neural Architecture Search with Batch Normalization

Boyu Chen et al.

Summary: BN-NAS is a method for accelerating neural architecture search using Batch Normalization, which predicts subnet performance and improves training efficiency by training only BN parameters.

2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021) (2021)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Joint Multi-Dimension Pruning via Numerical Gradient Update

Zechun Liu et al.

Summary: This study presents a joint multi-dimension pruning method, effectively pruning a network on three crucial aspects simultaneously. By defining the pruning vector, constructing a mapping from the vector to the pruned network structure, and optimizing the vector through numerical gradient optimization, the method collaboratively optimizes across dimensions and achieves better performance.

IEEE TRANSACTIONS ON IMAGE PROCESSING (2021)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence