Paper Reading AI Learner

Model soups to increase inference without increasing compute time

2023-01-24 15:59:07
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: this https URL

Abstract (translated)

在本文中,我们比较了模型汤在不同模型上的性能,包括ResNet、ViT和EfficientNet。我们使用了arXiv:2203.05482中的三个汤 recipe(贪婪汤排序、贪婪汤随机和均匀汤)并重复了作者的结果。然后,我们介绍了一种新的汤 recipe,称为削切汤。从汤中得出的结果比预训练视觉Transformer中的最优个体模型还要好,但对于ResNet和EfficientNet却表现得很糟糕。我们的削切汤表现比原始论文中的均匀和贪婪汤更好。我们还讨论了在实验中发现的权重平均限制。我们的模型汤库和与不同模型的实验代码可在这里找到:这个https URL。



3D Action Action_Localization Action_Recognition Activity Adversarial Agent Attention Autonomous Bert Boundary_Detection Caption Chat Classification CNN Compressive_Sensing Contour Contrastive_Learning Deep_Learning Denoising Detection Dialog Diffusion Drone Dynamic_Memory_Network Edge_Detection Embedding Embodied Emotion Enhancement Face Face_Detection Face_Recognition Facial_Landmark Few-Shot Gait_Recognition GAN Gaze_Estimation Gesture Gradient_Descent Handwriting Human_Parsing Image_Caption Image_Classification Image_Compression Image_Enhancement Image_Generation Image_Matting Image_Retrieval Inference Inpainting Intelligent_Chip Knowledge Knowledge_Graph Language_Model Matching Medical Memory_Networks Multi_Modal Multi_Task NAS NMT Object_Detection Object_Tracking OCR Ontology Optical_Character Optical_Flow Optimization Person_Re-identification Point_Cloud Portrait_Generation Pose Pose_Estimation Prediction QA Quantitative Quantitative_Finance Quantization Re-identification Recognition Recommendation Reconstruction Regularization Reinforcement_Learning Relation Relation_Extraction Represenation Represenation_Learning Restoration Review RNN Salient Scene_Classification Scene_Generation Scene_Parsing Scene_Text Segmentation Self-Supervised Semantic_Instance_Segmentation Semantic_Segmentation Semi_Global Semi_Supervised Sence_graph Sentiment Sentiment_Classification Sketch SLAM Sparse Speech Speech_Recognition Style_Transfer Summarization Super_Resolution Surveillance Survey Text_Classification Text_Generation Tracking Transfer_Learning Transformer Unsupervised Video_Caption Video_Classification Video_Indexing Video_Prediction Video_Retrieval Visual_Relation VQA Weakly_Supervised Zero-Shot