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 781790 of 10420 papers

TitleStatusHype
SparseFormer: Sparse Visual Recognition via Limited Latent TokensCode1
Adaptive Mask Sampling and Manifold to Euclidean Subspace Learning with Distance Covariance Representation for Hyperspectral Image ClassificationCode1
SMPConv: Self-moving Point Representations for Continuous ConvolutionCode1
EGC: Image Generation and Classification via a Diffusion Energy-Based ModelCode1
VNE: An Effective Method for Improving Deep Representation by Manipulating Eigenvalue DistributionCode1
Cross-modulated Few-shot Image Generation for Colorectal Tissue ClassificationCode1
Astroformer: More Data Might not be all you need for ClassificationCode1
Parents and Children: Distinguishing Multimodal DeepFakes from Natural ImagesCode1
Video Pretraining Advances 3D Deep Learning on Chest CT TasksCode1
Vision Transformers with Mixed-Resolution TokenizationCode1
Show:102550
← PrevPage 79 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