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 30313040 of 10420 papers

TitleStatusHype
A Deep Convolutional Neural Network Applied to Ship Detection and Classification0
Evaluating the Fairness of Neural Collapse in Medical Image Classification0
Boosting Video Captioning with Dynamic Loss Network0
An Encryption Method of ConvMixer Models without Performance Degradation0
An Empirical Study on the Efficacy of Deep Active Learning for Image Classification0
A Deep Bayesian Convolutional Spiking Neural Network-based CAD system with Uncertainty Quantification for Medical Images Classification0
Evaluating Data Augmentation Techniques for Coffee Leaf Disease Classification0
Adaptive Gradient Clipping for Robust Federated Learning0
A Deep and Autoregressive Approach for Topic Modeling of Multimodal Data0
An empirical study of the relation between network architecture and complexity0
Show:102550
← PrevPage 304 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