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 34913500 of 10420 papers

TitleStatusHype
Efficient On-device Training via Gradient FilteringCode1
GoogLe2Net: Going Transverse with Convolutions0
Neural Collapse in Deep Linear Networks: From Balanced to Imbalanced DataCode1
Chest X-Ray Images Classification with CNNCode0
TransIFC: Invariant Cues-aware Feature Concentration Learning for Efficient Fine-grained Bird Image Classification0
DiRaC-I: Identifying Diverse and Rare Training Classes for Zero-Shot Learning0
Machine Learning and Thermography Applied to the Detection and Classification of Cracks in Building0
Learning Multimodal Data Augmentation in Feature SpaceCode1
On Learning the Structure of Clusters in Graphs0
Thermal Heating in ReRAM Crossbar Arrays: Challenges and Solutions0
Show:102550
← PrevPage 350 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