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 96019625 of 10420 papers

TitleStatusHype
An Interaction-based Convolutional Neural Network (ICNN) Towards Better Understanding of COVID-19 X-ray ImagesCode0
Deep Learning for Classical Japanese LiteratureCode0
Neural Edge Histogram Descriptors for Underwater Acoustic Target RecognitionCode0
LayerAct: Advanced Activation Mechanism for Robust Inference of CNNsCode0
Deep Learning Development Environment in Virtual RealityCode0
Layer-Parallel Training of Deep Residual Neural NetworksCode0
BiRA-Net: Bilinear Attention Net for Diabetic Retinopathy GradingCode0
Activation Function Optimization Scheme for Image ClassificationCode0
Biomed-DPT: Dual Modality Prompt Tuning for Biomedical Vision-Language ModelsCode0
Compact and Optimal Deep Learning with Recurrent Parameter GeneratorsCode0
Deep Learning Based Automated COVID-19 Classification from Computed Tomography ImagesCode0
LayoutLMv3: Pre-training for Document AI with Unified Text and Image MaskingCode0
Neural Fingerprints for Adversarial Attack DetectionCode0
Neural Image Compression and ExplanationCode0
BioLCNet: Reward-modulated Locally Connected Spiking Neural NetworksCode0
An Information-Geometric Distance on the Space of TasksCode0
Neural Network Design: Learning from Neural Architecture SearchCode0
Precise Benchmarking of Explainable AI Attribution MethodsCode0
LDCSF: Local depth convolution-based Swim framework for classifying multi-label histopathology imagesCode0
L_DMI: An Information-theoretic Noise-robust Loss FunctionCode0
PRECISe : Prototype-Reservation for Explainable Classification under Imbalanced and Scarce-Data SettingsCode0
Neural Network QuineCode0
Deep Learning applied to NLPCode0
Adversarial Style Augmentation for Domain Generalized Urban-Scene SegmentationCode0
Recurrent Residual Convolutional Neural Network based on U-Net (R2U-Net) for Medical Image SegmentationCode0
Show:102550
← PrevPage 385 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