paper-with-me

홈 › Papers

LOTUS: Improving Transformer Efficiency with Sparsity Pruning and Data Lottery Tickets

2024-05-01 · Ojasw Upadhyay

Vision transformers have revolutionized computer vision, but their computational demands present challenges for training and deployment. This paper introduces LOTUS (LOttery Transformers with Ultra Sparsity), a novel method that leverages data lottery ticket selection and sparsity pruning to accelerate vision transformer training while maintaining accuracy. Our approach focuses on identifying and utilizing the most informative data subsets and eliminating redundant model parameters to optimize the training process. Through extensive experiments, we demonstrate the effectiveness of LOTUS in achieving rapid convergence and high accuracy with significantly reduced computational requirements. This work highlights the potential of combining data selection and sparsity techniques for efficient vision transformer training, opening doors for further research and development in this area.

📄 PDF Abstract BibTeX arXiv:2405.00906

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Multi-Head Attention 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Residual Connection 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Vision Transformer The Vision Transformer, or ViT, is a model for image classification that employs a Transformer-like architecture over…

Similar Papers 제목 키워드 기반

LoTUS: Large-Scale Machine Unlearning with a Taste of Uncertainty

2025-03-24 · CVPR 2025 1 · Christoforos N. Spartalis, Theodoros Semertzidis, Efstratios Gavves, Petros Daras

We present LoTUS, a novel Machine Unlearning (MU) method that eliminates the influence of training samples from pre-trained models, avoiding retraining from scratch. LoTUS smooths the prediction probabilities of the mode…

Machine UnlearningMemorization

Bridging the Gap Between Latent and Explicit Reasoning with Looped Transformers

2026-06-30 · Ying Fan, Anej Svete, Kangwook Lee arxiv

Language models typically reason via explicit chain-of-thought (CoT), generating intermediate steps token-by-token. Latent CoT offers an alternative: it performs multi-step reasoning in the model's hidden states, replaci…

Training Recipe for N:M Structured Sparsity with Decaying Pruning Mask

2022-09-15 · Sheng-Chun Kao, Amir Yazdanbakhsh, Suvinay Subramanian, Shivani Agrawal 외

Sparsity has become one of the promising methods to compress and accelerate Deep Neural Networks (DNNs). Among different categories of sparsity, structured sparsity has gained more attention due to its efficient executio…

Post-Training Statistical Calibration for Higher Activation Sparsity

2024-12-10 · Vui Seng Chua, Yujie Pan, Nilesh Jain

We present Statistical Calibrated Activation Pruning (SCAP), a post-training activation pruning framework that (1) generalizes sparsification by input activations of Fully-Connected layers for generic and flexible applic…

CP-ViT: Cascade Vision Transformer Pruning via Progressive Sparsity Prediction

2022-03-09 · Zhuoran Song, Yihong Xu, Zhezhi He, Li Jiang 외

Vision transformer (ViT) has achieved competitive accuracy on a variety of computer vision applications, but its computational cost impedes the deployment on resource-limited mobile devices. We explore the sparsity in Vi…