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 20512075 of 10420 papers

TitleStatusHype
Contextual Transformer Networks for Visual RecognitionCode1
Robust Learning Meets Generative Models: Can Proxy Distributions Improve Adversarial Robustness?Code1
Improving Generalization in Federated Learning by Seeking Flat MinimaCode1
Improving Zero-shot Generalization and Robustness of Multi-modal ModelsCode1
Improved Regularization of Convolutional Neural Networks with CutoutCode1
Improved Regularization and Robustness for Fine-tuning in Neural NetworksCode1
Improved Residual Networks for Image and Video RecognitionCode1
Improved Noisy Student Training for Automatic Speech RecognitionCode1
MViTv2: Improved Multiscale Vision Transformers for Classification and DetectionCode1
Improved Online Conformal Prediction via Strongly Adaptive Online LearningCode1
Improved Zero-Shot Classification by Adapting VLMs with Text DescriptionsCode1
Improved Baselines with Momentum Contrastive LearningCode1
Implicit-Zoo: A Large-Scale Dataset of Neural Implicit Functions for 2D Images and 3D ScenesCode1
Image sensing with multilayer, nonlinear optical neural networksCode1
A Simple Baseline for Semi-supervised Semantic Segmentation with Strong Data AugmentationCode1
Imbalanced Image Classification with Complement Cross EntropyCode1
A Simple Baseline for Low-Budget Active LearningCode1
CondenseNet V2: Sparse Feature Reactivation for Deep NetworksCode1
Content-aware Token Sharing for Efficient Semantic Segmentation with Vision TransformersCode1
IMPACT: A Large-scale Integrated Multimodal Patent Analysis and Creation Dataset for Design PatentsCode1
A Simple Interpretable Transformer for Fine-Grained Image Classification and AnalysisCode1
Contextual Convolutional Neural NetworksCode1
A Simple Semi-Supervised Learning Framework for Object DetectionCode1
Contextual Diversity for Active LearningCode1
Improved Generation of Adversarial Examples Against Safety-aligned LLMsCode1
Show:102550
← PrevPage 83 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
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
10Meta Pseudo Labels (EfficientNet-B6-Wide)Top 1 Accuracy90Unverified