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 89018925 of 10420 papers

TitleStatusHype
One-Class Feature Learning Using Intra-Class Splitting0
DAC: Data-free Automatic Acceleration of Convolutional NetworksCode0
An Empirical Evaluation of Sketched SVD and its Application to Leverage Score Ordering0
Semi-Supervised Deep Learning for Abnormality Classification in Retinal ImagesCode1
Toward Multimodal Model-Agnostic Meta-Learning0
TOP-GAN: Label-Free Cancer Cell Classification Using Deep Learning with a Small Training Set0
The Recognition Of Persian Phonemes Using PPNet0
Not Using the Car to See the Sidewalk: Quantifying and Controlling the Effects of Context in Classification and Segmentation0
Attending Category Disentangled Global Context for Image Classification0
Efficient Super Resolution Using Binarized Neural Network0
Pre-Trained Convolutional Neural Network Features for Facial Expression Recognition0
Flatten-T Swish: a thresholded ReLU-Swish-like activation function for deep learningCode0
Evolutionary Neural Architecture Search for Image Restoration0
Rethinking Layer-wise Feature Amounts in Convolutional Neural Network ArchitecturesCode0
Learning to Learn from Noisy Labeled DataCode0
Generating Hard Examples for Pixel-wise Classification0
Impact of Data Normalization on Deep Neural Network for Time Series Forecasting0
Thwarting Adversarial Examples: An L_0-RobustSparse Fourier Transform0
Reproduction Report on "Learn to Pay Attention"Code0
A Main/Subsidiary Network Framework for Simplifying Binary Neural Network0
ECG Arrhythmia Classification Using Transfer Learning from 2-Dimensional Deep CNN Features0
Layer-Parallel Training of Deep Residual Neural NetworksCode0
Proximal Mean-field for Neural Network QuantizationCode1
Defending Against Universal Perturbations With Shared Adversarial Training0
Feature Denoising for Improving Adversarial RobustnessCode0
Show:102550
← PrevPage 357 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