SOTAVerified

Image Classification

Image Classification is a fundamental task in vision recognition that aims to understand and categorize an image as a whole under a specific label. Unlike object detection, which involves classification and location of multiple objects within an image, image classification typically pertains to single-object images. When the classification becomes highly detailed or reaches instance-level, it is often referred to as image retrieval, which also involves finding similar images in a large database.

Source: Metamorphic Testing for Object Detection Systems

Papers

Showing 38013810 of 10420 papers

TitleStatusHype
TokenMixup: Efficient Attention-guided Token-level Data Augmentation for TransformersCode1
MEGCF: Multimodal Entity Graph Collaborative Filtering for Personalized RecommendationCode0
Sequential Learning Of Neural Networks for Prequential MDL0
Learnable Polyphase Sampling for Shift Invariant and Equivariant Convolutional NetworksCode1
Confidence estimation of classification based on the distribution of the neural network output layer0
WaveMix-Lite: A Resource-efficient Neural Network for Image AnalysisCode1
Equi-Tuning: Group Equivariant Fine-Tuning of Pretrained Models0
Improving the Reliability for Confidence Estimation0
SageMix: Saliency-Guided Mixup for Point CloudsCode1
Are Sample-Efficient NLP Models More Robust?0
Show:102550
← PrevPage 381 of 1042Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1CoCa (finetuned)Top 1 Accuracy91Unverified
2Model soups (BASIC-L)Top 1 Accuracy90.98Unverified
3Model soups (ViT-G/14)Top 1 Accuracy90.94Unverified
4DaViT-GTop 1 Accuracy90.4Unverified
5DaViT-HTop 1 Accuracy90.2Unverified
6Meta Pseudo Labels (EfficientNet-L2)Top 1 Accuracy90.2Unverified
7SwinV2-GTop 1 Accuracy90.17Unverified
8MAWS (ViT-6.5B)Top 1 Accuracy90.1Unverified
9Florence-CoSwin-HTop 1 Accuracy90.05Unverified
10RevCol-HTop 1 Accuracy90Unverified