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 86018625 of 10420 papers

TitleStatusHype
Bridging Lottery Ticket and Grokking: Understanding Grokking from Inner Structure of NetworksCode0
Analysing Training-Data Leakage from Gradients through Linear Systems and Gradient MatchingCode0
Efficient Global Neural Architecture SearchCode0
Efficient Feature Compression for Edge-Cloud SystemsCode0
Efficient Dynamic Attention 3D Convolution for Hyperspectral Image ClassificationCode0
Grounding Stylistic Domain Generalization with Quantitative Domain Shift Measures and Synthetic Scene ImagesCode0
Reproducibility study of "LICO: Explainable Models with Language-Image Consistency"Code0
Group Downsampling with Equivariant Anti-aliasingCode0
Grouped Pointwise Convolutions Significantly Reduces Parameters in EfficientNetCode0
Efficient Deep Spiking Multi-Layer Perceptrons with Multiplication-Free InferenceCode0
Fourier Transform Approximation as an Auxiliary Task for Image ClassificationCode0
Medical supervised masked autoencoders: Crafting a better masking strategy and efficient fine-tuning schedule for medical image classificationCode0
Efficient Decentralized Deep Learning by Dynamic Model AveragingCode0
Contextual Checkerboard Denoise -- A Novel Neural Network-Based Approach for Classification-Aware OCT Image DenoisingCode0
A Data-Driven Measure of Relative Uncertainty for Misclassification DetectionCode0
Growing a Brain with Sparsity-Inducing Generation for Continual LearningCode0
An All-digital 8.6-nJ/Frame 65-nm Tsetlin Machine Image Classification AcceleratorCode0
An Algorithm for Out-Of-Distribution Attack to Neural Network EncoderCode0
Efficient CNN Architecture Design Guided by VisualizationCode0
Guarantees of confidentiality via Hammersley-Chapman-Robbins boundsCode0
Guessing Smart: Biased Sampling for Efficient Black-Box Adversarial AttacksCode0
Context-Gated ConvolutionCode0
Guidelines and Benchmarks for Deployment of Deep Learning Models on Smartphones as Real-Time AppsCode0
Context-Aware Compilation of DNN Training Pipelines across Edge and CloudCode0
Constructing Multiple Tasks for Augmentation: Improving Neural Image Classification With K-means FeaturesCode0
Show:102550
← PrevPage 345 of 417Next →

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
10Meta Pseudo Labels (EfficientNet-B6-Wide)Top 1 Accuracy90Unverified