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 81268150 of 10420 papers

TitleStatusHype
FedDUAL: A Dual-Strategy with Adaptive Loss and Dynamic Aggregation for Mitigating Data Heterogeneity in Federated LearningCode0
Artificial intelligence based glaucoma and diabetic retinopathy detection using MATLAB — retrained AlexNet convolutional neural networkCode0
Artificial Generation of Big Data for Improving Image Classification: A Generative Adversarial Network Approach on SAR DataCode0
Retinal Fundus Multi-Disease Image Classification using Hybrid CNN-Transformer-Ensemble ArchitecturesCode0
Delving into the Openness of CLIPCode0
Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video ClassificationCode0
Rethinking Softmax with Cross-Entropy: Neural Network Classifier as Mutual Information EstimatorCode0
Feature transforms for image data augmentationCode0
Complementing Representation Deficiency in Few-shot Image Classification: A Meta-Learning ApproachCode0
Rethinking Normalization and Elimination Singularity in Neural NetworksCode0
Rethinking Layer-wise Feature Amounts in Convolutional Neural Network ArchitecturesCode0
Rethinking Label Smoothing on Multi-hop Question AnsweringCode0
Feature Normalized Knowledge Distillation for Image ClassificationCode0
Competing Ratio Loss for Discriminative Multi-class Image ClassificationCode0
A Rotation Meanout Network with Invariance for Dermoscopy Image Classification and RetrievalCode0
Rethinking Feature Distribution for Loss Functions in Image ClassificationCode0
Rethinking deep active learning: Using unlabeled data at model trainingCode0
Feature Fusion via Multiresolution Compressive Measurement Matrix Analysis For Spectral Image ClassificationCode0
ReSpike: Residual Frames-based Hybrid Spiking Neural Networks for Efficient Action RecognitionCode0
Resolution-Invariant Image Classification based on Fourier Neural OperatorsCode0
Feature Denoising for Improving Adversarial RobustnessCode0
ARMA Nets: Expanding Receptive Field for Dense PredictionCode0
ResNet-like Architecture with Low Hardware RequirementsCode0
Comparison Knowledge Translation for Generalizable Image ClassificationCode0
Feasible LearningCode0
Show:102550
← PrevPage 326 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
10RevCol-HTop 1 Accuracy90Unverified