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 761770 of 10420 papers

TitleStatusHype
Multistage Relation Network With Dual-Metric for Few-Shot Hyperspectral Image ClassificationCode1
From Association to Generation: Text-only Captioning by Unsupervised Cross-modal MappingCode1
Deep Fast Vision: Accelerated Deep Transfer Learning Vision Prototyping and BeyondCode1
ESPT: A Self-Supervised Episodic Spatial Pretext Task for Improving Few-Shot LearningCode1
Bayesian Optimization Meets Self-DistillationCode1
MixPro: Data Augmentation with MaskMix and Progressive Attention Labeling for Vision TransformerCode1
Function-Consistent Feature DistillationCode1
AwesomeMeta+: A Mixed-Prototyping Meta-Learning System Supporting AI Application Design AnywhereCode1
Learning Partial Correlation based Deep Visual Representation for Image ClassificationCode1
Learning Bottleneck Concepts in Image ClassificationCode1
Show:102550
← PrevPage 77 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
5Meta Pseudo Labels (EfficientNet-L2)Top 1 Accuracy90.2Unverified
6DaViT-HTop 1 Accuracy90.2Unverified
7SwinV2-GTop 1 Accuracy90.17Unverified
8MAWS (ViT-6.5B)Top 1 Accuracy90.1Unverified
9Florence-CoSwin-HTop 1 Accuracy90.05Unverified
10RevCol-HTop 1 Accuracy90Unverified