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 27812790 of 10420 papers

TitleStatusHype
Improving robustness to corruptions with multiplicative weight perturbationsCode0
Improvising the Learning of Neural Networks on Hyperspherical ManifoldCode0
Instilling Inductive Biases with SubnetworksCode0
Learning the Space of Deep ModelsCode0
Acne Severity Grading on Face Images via Extraction and Guidance of Prior KnowledgeCode0
Boosting Ensemble Accuracy by Revisiting Ensemble Diversity MetricsCode0
Boosting Domain Incremental Learning: Selecting the Optimal Parameters is All You NeedCode0
Improving Deep Neural Network Random Initialization Through Neuronal RewiringCode0
Improving Classification Neural Networks by using Absolute activation function (MNIST/LeNET-5 example)Code0
An Empirical Investigation of Randomized Defenses against Adversarial AttacksCode0
Show:102550
← PrevPage 279 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
10RevCol-HTop 1 Accuracy90Unverified