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 52515275 of 10420 papers

TitleStatusHype
Grouped Pointwise Convolutions Significantly Reduces Parameters in EfficientNetCode0
Non-deep NetworksCode1
FocusNet: Classifying Better by Focusing on Confusing ClassesCode1
Self-Supervised Learning by Estimating Twin Class DistributionsCode1
Adversarial Attack across Datasets0
Scaling Laws for the Few-Shot Adaptation of Pre-trained Image Classifiers0
Subspace Regularizers for Few-Shot Class Incremental LearningCode1
Well-classified Examples are Underestimated in Classification with Deep Neural NetworksCode1
Transform and Bitstream Domain Image Classification0
Bio-inspired learnable divisive normalization for ANNs0
NAS-Bench-360: Benchmarking Neural Architecture Search on Diverse TasksCode1
Voice-assisted Image Labelling for Endoscopic Ultrasound Classification using Neural Networks0
Dynamic Inference with Neural Interpreters0
Balancing Average and Worst-case Accuracy in Multitask Learning0
CovXR: Automated Detection of COVID-19 Pneumonia in Chest X-Rays through Machine Learning0
Semi-Supervised Auto-Encoder Graph Network for Diabetic Retinopathy Grading0
Decomposing Convolutional Neural Networks into Reusable and Replaceable Modules0
A Closer Look at Prototype Classifier for Few-shot Image Classification0
Synthesizing Machine Learning Programs with PAC Guarantees via Statistical Sketching0
Homogeneous Learning: Self-Attention Decentralized Deep LearningCode0
Instance-based Label Smoothing For Better Calibrated Classification NetworksCode0
Revitalizing CNN Attentions via Transformers in Self-Supervised Visual Representation LearningCode1
Learnable Adaptive Cosine Estimator (LACE) for Image ClassificationCode0
Momentum Centering and Asynchronous Update for Adaptive Gradient MethodsCode2
Heavy Ball Neural Ordinary Differential EquationsCode1
Show:102550
← PrevPage 211 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