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 25412550 of 10420 papers

TitleStatusHype
Classification Beats Regression: Counting of Cells from Greyscale Microscopic Images based on Annotation-free Training SamplesCode0
Improving Transferability of Adversarial Examples with Input DiversityCode0
Improving the repeatability of deep learning models with Monte Carlo dropoutCode0
Improving the Gating Mechanism of Recurrent Neural NetworksCode0
Improving the trustworthiness of image classification models by utilizing bounding-box annotationsCode0
Improvising the Learning of Neural Networks on Hyperspherical ManifoldCode0
Revisiting 16-bit Neural Network Training: A Practical Approach for Resource-Limited LearningCode0
A Consensual Collaborative Learning Method for Remote Sensing Image Classification Under Noisy Multi-LabelsCode0
Improving singing voice separation with the Wave-U-Net using Minimum Hyperspherical EnergyCode0
Improving robustness to corruptions with multiplicative weight perturbationsCode0
Show:102550
← PrevPage 255 of 1042Next →

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