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 45264550 of 10420 papers

TitleStatusHype
Safeguarding Data in Multimodal AI: A Differentially Private Approach to CLIP TrainingCode0
Resource Efficient Neural Networks Using Hessian Based Pruning0
Rotational augmentation techniques: a new perspective on ensemble learning for image classification0
Scale-Rotation-Equivariant Lie Group Convolution Neural Networks (Lie Group-CNNs)0
Augmenting Zero-Shot Detection Training with Image Labels0
Active Globally Explainable Learning for Medical Images via Class Association Embedding and Cyclic Adversarial Generation0
Neural Architecture Design and Robustness: A Dataset0
Computational and Storage Efficient Quadratic Neurons for Deep Neural Networks0
Higher Chest X-ray Resolution Improves Classification Performance0
Hidden Classification Layers: Enhancing linear separability between classes in neural networks layers0
Understanding the Effect of the Long Tail on Neural Network Compression0
Leveraging Large Language Models for Scalable Vector Graphics-Driven Image UnderstandingCode0
Contrastive Learning for Predicting Cancer Prognosis Using Gene Expression ValuesCode0
LayerAct: Advanced Activation Mechanism for Robust Inference of CNNsCode0
A Melting Pot of Evolution and Learning0
Regularizing with Pseudo-Negatives for Continual Self-Supervised LearningCode0
T-ADAF: Adaptive Data Augmentation Framework for Image Classification Network based on Tensor T-product Operator0
GeoDiffusion: Text-Prompted Geometric Control for Object Detection Data Generation0
Quantitative Analysis of Primary Attribution Explainable Artificial Intelligence Methods for Remote Sensing Image ClassificationCode0
Quick-Tune: Quickly Learning Which Pretrained Model to Finetune and How0
Human-imperceptible, Machine-recognizable ImagesCode0
Input-gradient space particle inference for neural network ensemblesCode0
Semantically-Prompted Language Models Improve Visual Descriptions0
Continual Learning with Pretrained Backbones by Tuning in the Input Space0
Resilient Constrained Learning0
Show:102550
← PrevPage 182 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