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 76517675 of 10420 papers

TitleStatusHype
Policy-Based Federated LearningCode0
FrImCla: A Framework for Image Classification Using Traditional and Transfer Learning TechniquesCode0
The GraphNet Zoo: An All-in-One Graph Based Deep Semi-Supervised Framework for Medical Image Classification0
Extended Batch Normalization0
SOS: Selective Objective Switch for Rapid Immunofluorescence Whole Slide Image ClassificationCode1
GPCA: A Probabilistic Framework for Gaussian Process Embedded Channel AttentionCode0
Learning to be Global Optimizer0
LIMEADE: From AI Explanations to Advice TakingCode0
Improved Baselines with Momentum Contrastive LearningCode1
Implementation of Deep Neural Networks to Classify EEG Signals using Gramian Angular Summation Field for Epilepsy Diagnosis0
Π-nets: Deep Polynomial Neural NetworksCode1
Clean-Label Backdoor Attacks on Video Recognition ModelsCode1
SimLoss: Class Similarities in Cross EntropyCode1
TaskNorm: Rethinking Batch Normalization for Meta-LearningCode1
Decentralized SGD with Over-the-Air Computation0
AIDeveloper: deep learning image classification in life science and beyondCode1
Search Space of Adversarial Perturbations against Image Filters0
Accelerator-aware Neural Network Design using AutoML0
Feature Extraction for Hyperspectral Imagery: The Evolution from Shallow to Deep (Overview and Toolbox)Code1
Combating noisy labels by agreement: A joint training method with co-regularizationCode1
Metrics and methods for robustness evaluation of neural networks with generative modelsCode0
Denoised Smoothing: A Provable Defense for Pretrained ClassifiersCode1
Joint Device-Edge Inference over Wireless Links with Pruning0
A multiple-instance densely-connected ConvNet for aerial scene classificationCode0
On the rate of convergence of image classifiers based on convolutional neural networks0
Show:102550
← PrevPage 307 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