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 531540 of 10419 papers

TitleStatusHype
Curriculum Labeling: Revisiting Pseudo-Labeling for Semi-Supervised LearningCode1
Decision Stream: Cultivating Deep Decision TreesCode1
Contrastive Learning of Medical Visual Representations from Paired Images and TextCode1
Contrastive Losses Are Natural Criteria for Unsupervised Video SummarizationCode1
A Second-Order Approach to Learning with Instance-Dependent Label NoiseCode1
Grafting Transformer on Automatically Designed Convolutional Neural Network for Hyperspectral Image ClassificationCode1
Contrastive Learning of Generalized Game RepresentationsCode1
Contrastive Masked Autoencoders are Stronger Vision LearnersCode1
Understanding the Role of the Projector in Knowledge DistillationCode1
Addressing Failure Prediction by Learning Model ConfidenceCode1
Show:102550
← PrevPage 54 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