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 20012010 of 10420 papers

TitleStatusHype
Theory-Inspired Path-Regularized Differential Network Architecture SearchCode1
The Reversible Residual Network: Backpropagation Without Storing ActivationsCode1
Hamiltonian Deep Neural Networks Guaranteeing Non-vanishing Gradients by DesignCode1
Hard-Attention for Scalable Image ClassificationCode1
HarDNet-MSEG: A Simple Encoder-Decoder Polyp Segmentation Neural Network that Achieves over 0.9 Mean Dice and 86 FPSCode1
Hard Sample Aware Noise Robust Learning for Histopathology Image ClassificationCode1
Concurrent Spatial and Channel Squeeze & Excitation in Fully Convolutional NetworksCode1
Harmonic Convolutional Networks based on Discrete Cosine TransformCode1
Harmonic Networks with Limited Training SamplesCode1
Hyperbolic Image-Text RepresentationsCode1
Show:102550
← PrevPage 201 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