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 61016125 of 10420 papers

TitleStatusHype
Combined Depth Space based Architecture Search For Person Re-identificationCode0
Class-Wise Principal Component Analysis for hyperspectral image feature extraction0
eGAN: Unsupervised approach to class imbalance using transfer learningCode0
Self-Weighted Ensemble Method to Adjust the Influence of Individual Models based on Reliability0
Direct Differentiable Augmentation SearchCode1
Reinforced Attention for Few-Shot Learning and Beyond0
Robust Training of Social Media Image Classification Models for Rapid Disaster Response0
Unsupervised Class-Incremental Learning Through Confusion0
CondenseNet V2: Sparse Feature Reactivation for Deep NetworksCode1
Few-Shot Action Recognition with Compromised Metric via Optimal Transport0
Robust Self-Ensembling Network for Hyperspectral Image ClassificationCode1
Robust Differentiable SVDCode1
Deep Features for training Support Vector Machine0
HindSight: A Graph-Based Vision Model Architecture For Representing Part-Whole Hierarchies0
Prototypical Region Proposal Networks for Few-Shot Localization and Classification0
Quantum Enhanced Filter: QFilter0
Distilling and Transferring Knowledge via cGAN-generated Samples for Image Classification and RegressionCode0
Streaming Self-Training via Domain-Agnostic Unlabeled Images0
White Box Methods for Explanations of Convolutional Neural Networks in Image Classification Tasks0
Dopamine Transporter SPECT Image Classification for Neurodegenerative Parkinsonism via Diffusion Maps and Machine Learning Classifiers0
Robust Semantic Interpretability: Revisiting Concept Activation VectorsCode1
Beyond Categorical Label Representations for Image ClassificationCode1
Tuned Compositional Feature Replays for Efficient Stream LearningCode0
Classification with Runge-Kutta networks and feature space augmentationCode0
Fourier Image TransformerCode1
Show:102550
← PrevPage 245 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
10RevCol-HTop 1 Accuracy90Unverified