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 8190 of 10419 papers

TitleStatusHype
Bag of Freebies for Training Object Detection Neural NetworksCode3
Cascade Prompt Learning for Vision-Language Model AdaptationCode3
MaxViT: Multi-Axis Vision TransformerCode3
FusionBench: A Comprehensive Benchmark of Deep Model FusionCode3
Momentum Contrast for Unsupervised Visual Representation LearningCode3
Falcon: A Remote Sensing Vision-Language Foundation ModelCode3
FastViT: A Fast Hybrid Vision Transformer using Structural ReparameterizationCode3
EfficientNetV2: Smaller Models and Faster TrainingCode3
EfficientNet: Rethinking Model Scaling for Convolutional Neural NetworksCode3
XCiT: Cross-Covariance Image TransformersCode3
Show:102550
← PrevPage 9 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