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 17511775 of 10420 papers

TitleStatusHype
A Novel lightweight Convolutional Neural Network, ExquisiteNetV2Code1
Evaluating the Adversarial Robustness of Adaptive Test-time DefensesCode1
Adaptive Rational Activations to Boost Deep Reinforcement LearningCode1
Reduced Precision Floating-Point Optimization for Deep Neural Network On-Device Learning on MicroControllersCode1
Co^2L: Contrastive Continual LearningCode1
Evaluating histopathology transfer learning with ChampKitCode1
RegionCLIP: Region-based Language-Image PretrainingCode1
Region Comparison Network for Interpretable Few-shot Image ClassificationCode1
EViT: An Eagle Vision Transformer with Bi-Fovea Self-AttentionCode1
EXACT: How to Train Your AccuracyCode1
Circumventing Outliers of AutoAugment with Knowledge DistillationCode1
Evaluating the visualization of what a Deep Neural Network has learnedCode1
Evidential Turing ProcessesCode1
Evaluation of Deep Neural Network Domain Adaptation Techniques for Image RecognitionCode1
Re-labeling ImageNet: from Single to Multi-Labels, from Global to Localized LabelsCode1
Relational Surrogate Loss LearningCode1
Co2L: Contrastive Continual LearningCode1
Evolutionary Neural AutoML for Deep LearningCode1
Evolving Attention with Residual ConvolutionsCode1
Class-Aware Contrastive Semi-Supervised LearningCode1
Class-Aware Patch Embedding Adaptation for Few-Shot Image ClassificationCode1
Class-Balanced Active Learning for Image ClassificationCode1
Class-Balanced Distillation for Long-Tailed Visual RecognitionCode1
Class-Balanced Loss Based on Effective Number of SamplesCode1
LR-Net: A Block-based Convolutional Neural Network for Low-Resolution Image ClassificationCode1
Show:102550
← PrevPage 71 of 417Next →

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