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 40514060 of 10420 papers

TitleStatusHype
MixSKD: Self-Knowledge Distillation from Mixup for Image RecognitionCode1
Self-Knowledge Distillation via Dropout0
Patching open-vocabulary models by interpolating weightsCode1
PatchDropout: Economizing Vision Transformers Using Patch DropoutCode1
Machine Learning with DBOS0
Combining Stochastic Defenses to Resist Gradient Inversion: An Ablation Study0
SBPF: Sensitiveness Based Pruning Framework For Convolutional Neural Network On Image Classification0
On the Activation Function Dependence of the Spectral Bias of Neural Networks0
All-optical image classification through unknown random diffusers using a single-pixel diffractive network0
No More Strided Convolutions or Pooling: A New CNN Building Block for Low-Resolution Images and Small ObjectsCode2
Show:102550
← PrevPage 406 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
10RevCol-HTop 1 Accuracy90Unverified