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 29763000 of 10420 papers

TitleStatusHype
Improving Shift Invariance in Convolutional Neural Networks with Translation Invariant Polyphase SamplingCode0
BioLCNet: Reward-modulated Locally Connected Spiking Neural NetworksCode0
Delving into Transferable Adversarial Examples and Black-box AttacksCode0
Improving Generalizability of Kolmogorov-Arnold Networks via Error-Correcting Output CodesCode0
Improving Fairness in Image Classification via SketchingCode0
Improving Generalization and Convergence by Enhancing Implicit RegularizationCode0
Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet ClassificationCode0
Improving Deep Neural Network Random Initialization Through Neuronal RewiringCode0
Delayed Memory Unit: Modelling Temporal Dependency Through Delay GateCode0
Improving Ensemble Distillation With Weight Averaging and Diversifying PerturbationCode0
Improving Classification Neural Networks by using Absolute activation function (MNIST/LeNET-5 example)Code0
Improving Calibration by Relating Focal Loss, Temperature Scaling, and PropernessCode0
Differentially Private Image Classification from FeaturesCode0
Improving Confident-Classifiers For Out-of-distribution DetectionCode0
Improving (α, f)-Byzantine Resilience in Federated Learning via layerwise aggregation and cosine distanceCode0
Classification Utility, Fairness, and Compactness via Tunable Information Bottleneck and Rényi MeasuresCode0
Towards Difficulty-Agnostic Efficient Transfer Learning for Vision-Language ModelsCode0
Differential Privacy Has Disparate Impact on Model AccuracyCode0
BiRA-Net: Bilinear Attention Net for Diabetic Retinopathy GradingCode0
DiffExplainer: Unveiling Black Box Models Via Counterfactual GenerationCode0
DiffFormer: a Differential Spatial-Spectral Transformer for Hyperspectral Image ClassificationCode0
FTBNN: Rethinking Non-linearity for 1-bit CNNs and Going BeyondCode0
Deformable Kernels: Adapting Effective Receptive Fields for Object DeformationCode0
Improving Generalization of Batch Whitening by Convolutional Unit OptimizationCode0
Improved Training Speed, Accuracy, and Data Utilization Through Loss Function OptimizationCode0
Show:102550
← PrevPage 120 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
5Meta Pseudo Labels (EfficientNet-L2)Top 1 Accuracy90.2Unverified
6DaViT-HTop 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