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 31013125 of 10420 papers

TitleStatusHype
Improving k-Means Clustering Performance with Disentangled Internal RepresentationsCode0
Improving Generalizability of Kolmogorov-Arnold Networks via Error-Correcting Output CodesCode0
Deep Sub-Ensembles for Fast Uncertainty Estimation in Image ClassificationCode0
An Algorithm for Out-Of-Distribution Attack to Neural Network EncoderCode0
Improving Generalization and Convergence by Enhancing Implicit RegularizationCode0
Improving Long-tailed Object Detection with Image-Level Supervision by Multi-Task Collaborative LearningCode0
DeepSplit: Scalable Verification of Deep Neural Networks via Operator SplittingCode0
Rationally Inattentive Utility Maximization for Interpretable Deep Image ClassificationCode0
Improving Deep Neural Network Random Initialization Through Neuronal RewiringCode0
Improving Ensemble Distillation With Weight Averaging and Diversifying PerturbationCode0
BDNet: Bengali Handwritten Numeral Digit Recognition based on Densely connected Convolutional Neural NetworksCode0
Excitement Surfeited Turns to Errors: Deep Learning Testing Framework Based on Excitable NeuronsCode0
Improving Confident-Classifiers For Out-of-distribution DetectionCode0
Improving Fairness in Image Classification via SketchingCode0
Improving singing voice separation with the Wave-U-Net using Minimum Hyperspherical EnergyCode0
BayTTA: Uncertainty-aware medical image classification with optimized test-time augmentation using Bayesian model averagingCode0
Towards Difficulty-Agnostic Efficient Transfer Learning for Vision-Language ModelsCode0
Distributed Learning of Deep Neural Networks using Independent Subnet TrainingCode0
An AI-Powered VVPAT Counter for Elections in IndiaCode0
DeepSearch: A Simple and Effective Blackbox Attack for Deep Neural NetworksCode0
Adaptive Randomized Smoothing: Certified Adversarial Robustness for Multi-Step DefencesCode0
LIMEtree: Consistent and Faithful Multi-class ExplanationsCode0
Bayesian Robust Aggregation for Federated LearningCode0
Lipsum-FT: Robust Fine-Tuning of Zero-Shot Models Using Random Text GuidanceCode0
DeepSat V2: Feature Augmented Convolutional Neural Nets for Satellite Image ClassificationCode0
Show:102550
← PrevPage 125 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