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 34613470 of 10420 papers

TitleStatusHype
Adaptive and Background-Aware Vision Transformer for Real-Time UAV TrackingCode1
Automated Knowledge Distillation via Monte Carlo Tree SearchCode0
Self-supervised Pre-training for Mirror Detection0
Growing a Brain with Sparsity-Inducing Generation for Continual LearningCode0
XiNet: Efficient Neural Networks for tinyML0
Rethinking Fast Fourier Convolution in Image Inpainting0
Vision HGNN: An Image is More than a Graph of NodesCode1
RA-CLIP: Retrieval Augmented Contrastive Language-Image Pre-Training0
PIP-Net: Patch-Based Intuitive Prototypes for Interpretable Image ClassificationCode1
A New Dataset Based on Images Taken by Blind People for Testing the Robustness of Image Classification Models Trained for ImageNet CategoriesCode0
Show:102550
← PrevPage 347 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