paper-with-me

Papers

Model soups to increase inference without increasing compute time

2023-01-24 · Charles Dansereau, Milo Sobral, Maninder Bhogal, Mehdi Zalai

In this paper, we compare Model Soups performances on three different models (ResNet, ViT and EfficientNet) using three Soup Recipes (Greedy Soup Sorted, Greedy Soup Random and Uniform soup) from arXiv:2203.05482, and reproduce the results of the authors. We then introduce a new Soup Recipe called Pruned Soup. Results from the soups were better than the best individual model for the pre-trained vision transformer, but were much worst for the ResNet and the EfficientNet. Our pruned soup performed better than the uniform and greedy soups presented in the original paper. We also discuss the limitations of weight-averaging that were found during the experiments. The code for our model soup library and the experiments with different models can be found here: https://github.com/milo-sobral/ModelSoup

📄 PDF Abstract BibTeX arXiv:2301.10092

Code (1)

milo-sobral/modelsoup 공식 구현 pytorch

Methods 이 논문이 사용한 방법론

Library 설명 없음
Soups Compress an ensemble of models into a single one by averaging their weights (under certain pre-conditions).
ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Depthwise Convolution Depthwise Convolution is a type of convolution where we apply a single convolutional filter for each input channel. In the regular 2D…
Pointwise Convolution Pointwise Convolution is a type of convolution that uses a 1x1 kernel: a kernel that iterates through every single point. This…
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…
Kaiming Initialization 설명 없음
Depthwise Separable Convolution While standard convolution performs the channelwise and spatial-wise computation in one step, Depthwise Separable Convolution

Similar Papers 제목 키워드 기반

Adversarial Example Soups: Improving Transferability and Stealthiness for Free

2024-02-27 · Bo Yang, Hengwei Zhang, Jindong Wang, Yulong Yang 외

Transferable adversarial examples cause practical security risks since they can mislead a target model without knowing its internal knowledge. A conventional recipe for maximizing transferability is to keep only the opti…

Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time

2022-03-10 · Mitchell Wortsman, Gabriel Ilharco, Samir Yitzhak Gadre, Rebecca Roelofs 외

The conventional recipe for maximizing model accuracy is to (1) train multiple models with various hyperparameters and (2) pick the individual model which performs best on a held-out validation set, discarding the remain…

Domain Generalizationimage-classificationImage Classification+2

RADIN: Souping on a Budget

2024-01-31 · Thibaut Menes, Olivier Risser-Maroix

Model Soups, extending Stochastic Weights Averaging (SWA), combine models fine-tuned with different hyperparameters. Yet, their adoption is hindered by computational challenges due to subset selection issues. In this pap…

Ensemble LearningModel Compression

Sparse Model Soups: A Recipe for Improved Pruning via Model Averaging

2023-06-29 · Max Zimmer, Christoph Spiegel, Sebastian Pokutta

Neural networks can be significantly compressed by pruning, yielding sparse models with reduced storage and computational demands while preserving predictive performance. Model soups (Wortsman et al., 2022) enhance gener…

model

Enhanced Soups for Graph Neural Networks

2025-03-14 · Joseph Zuber, Aishwarya Sarkar, Joseph Jennings, Ali Jannesari

Graph Neural Networks (GNN) have demonstrated state-of-the-art performance in numerous scientific and high-performance computing (HPC) applications. Recent work suggests that "souping" (combining) individually trained GN…