HyperAI초신경

홈 뉴스 최신 연구 논문 튜토리얼 데이터셋 백과사전 SOTA LLM 모델 GPU 랭킹 컨퍼런스

한국어

HyperAI초신경

Fine Grained Image Classification On Oxford 2

평가 지표

Accuracy

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	Accuracy	Paper Title	Repository
ResNet-50-SAM	91.6	When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations
µ2Net (ViT-L/16)	95.3	An Evolutionary Approach to Dynamic Introduction of Tasks in Large-scale Multitask Learning Systems
Assemble-ResNet-FGVC-50	94.3%	Compounding the Performance Improvements of Assembled Techniques in a Convolutional Neural Network
NAT-M3	94.1	Neural Architecture Transfer
Mixer-B/16- SAM	92.5	When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations
ResNet-101 (ideal number of groups)	77.076	On the Ideal Number of Groups for Isometric Gradient Propagation	-
NAT-M2	93.5	Neural Architecture Transfer
PreResNet-101	85.5897	How to Use Dropout Correctly on Residual Networks with Batch Normalization
Mixer-S/16- SAM	88.7	When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations
SE-ResNet-101 (SAP)	86.011	Stochastic Subsampling With Average Pooling	-
µ2Net+ (ViT-L/16)	95.5	A Continual Development Methodology for Large-scale Multitask Dynamic ML Systems
EffNet-L2 (SAM)	97.10	Sharpness-Aware Minimization for Efficiently Improving Generalization
NAT-M4	94.3	Neural Architecture Transfer
ViT-B/16- SAM	93.1	When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations
BiT-L (ResNet)	96.62	Big Transfer (BiT): General Visual Representation Learning
ViT-S/16- SAM	92.9	When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations
ResNet-152-SAM	93.3	When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentations
BiT-M (ResNet)	94.47	Big Transfer (BiT): General Visual Representation Learning
ViT-B/16	-	An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale

0 of 19 row(s) selected.