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 30513075 of 10420 papers

TitleStatusHype
KGTN-ens: Few-Shot Image Classification with Knowledge Graph EnsemblesCode0
Improving Deep Neural Network Random Initialization Through Neuronal RewiringCode0
Benchmarking Deep Learning Models on NVIDIA Jetson Nano for Real-Time Systems: An Empirical InvestigationCode0
Discretize-Optimize vs. Optimize-Discretize for Time-Series Regression and Continuous Normalizing FlowsCode0
Deep Visual City Recognition VisualizationCode0
Adaptive Sample Selection for Robust Learning under Label NoiseCode0
Discriminative Active LearningCode0
Boosting Deep Ensemble Performance with Hierarchical PruningCode0
An Empirical Investigation of Randomized Defenses against Adversarial AttacksCode0
Discriminative Feature Learning through Feature Distance LossCode0
Deep Variation-structured Reinforcement Learning for Visual Relationship and Attribute DetectionCode0
Analysing Training-Data Leakage from Gradients through Linear Systems and Gradient MatchingCode0
Improving Ensemble Distillation With Weight Averaging and Diversifying PerturbationCode0
Improving (α, f)-Byzantine Resilience in Federated Learning via layerwise aggregation and cosine distanceCode0
Improving Calibration by Relating Focal Loss, Temperature Scaling, and PropernessCode0
Benchmark Generation Framework with Customizable Distortions for Image Classifier RobustnessCode0
Improving Classification Neural Networks by using Absolute activation function (MNIST/LeNET-5 example)Code0
Deep transfer learning method based on automatic domain alignment and moment matchingCode0
Fourier Transform Approximation as an Auxiliary Task for Image ClassificationCode0
Discriminative Unsupervised Feature Learning with Convolutional Neural NetworksCode0
BR-NPA: A Non-Parametric High-Resolution Attention Model to improve the Interpretability of AttentionCode0
Towards Difficulty-Agnostic Efficient Transfer Learning for Vision-Language ModelsCode0
Improving Confident-Classifiers For Out-of-distribution DetectionCode0
Improving Fairness in Image Classification via SketchingCode0
An All-digital 8.6-nJ/Frame 65-nm Tsetlin Machine Image Classification AcceleratorCode0
Show:102550
← PrevPage 123 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