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 40614070 of 10420 papers

TitleStatusHype
Compressed Domain Image Classification Using a Dynamic-Rate Neural Network0
ARTxAI: Explainable Artificial Intelligence Curates Deep Representation Learning for Artistic Images using Fuzzy Techniques0
Federated Variational Inference: Towards Improved Personalization and Generalization0
Beyond cross-entropy: learning highly separable feature distributions for robust and accurate classification0
FedGEMS: Federated Learning of Larger Server Models via Selective Knowledge Fusion0
FedGSCA: Medical Federated Learning with Global Sample Selector and Client Adaptive Adjuster under Label Noise0
Analyzing Filters Toward Efficient ConvNet0
Dermoscopic Image Classification with Neural Style Transfer0
Depthwise-STFT based separable Convolutional Neural Networks0
Depthwise Separable Convolutions Allow for Fast and Memory-Efficient Spectral Normalization0
Show:102550
← PrevPage 407 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