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 38113820 of 10420 papers

TitleStatusHype
ERNIE-Layout: Layout Knowledge Enhanced Pre-training for Visually-rich Document UnderstandingCode1
Multi-Granularity Cross-modal Alignment for Generalized Medical Visual Representation LearningCode1
Image Projective Transformation Rectification with Synthetic Data for Smartphone-captured Chest X-ray Photos ClassificationCode0
Semantic Cross Attention for Few-shot LearningCode0
Token-Label Alignment for Vision TransformersCode1
Deep Combinatorial AggregationCode0
Latency-aware Spatial-wise Dynamic NetworksCode1
On Divergence Measures for Bayesian PseudocoresetsCode0
A Unified Framework with Meta-dropout for Few-shot Learning0
Deep Active Ensemble Sampling For Image Classification0
Show:102550
← PrevPage 382 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