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 26512700 of 10419 papers

TitleStatusHype
Capsule Routing via Variational BayesCode0
In-domain representation learning for remote sensingCode0
Influence of Image Classification Accuracy on Saliency Map EstimationCode0
Initialization Matters for Adversarial Transfer LearningCode0
Instance Enhancement Batch Normalization: an Adaptive Regulator of Batch NoiseCode0
LarvSeg: Exploring Image Classification Data For Large Vocabulary Semantic Segmentation via Category-wise Attentive ClassifierCode0
Capsule Networks against Medical Imaging Data ChallengesCode0
An Intriguing Failing of Convolutional Neural Networks and the CoordConv SolutionCode0
Increasing-Margin Adversarial (IMA) Training to Improve Adversarial Robustness of Neural NetworksCode0
CapsuleGAN: Generative Adversarial Capsule NetworkCode0
A Comparative Study on Efficiencies of Variants of Convolutional Neural Networks based on Image Classification TaskCode0
Advancements in Medical Image Classification through Fine-Tuning Natural Domain Foundation ModelsCode0
An interpretable automated detection system for FISH-based HER2 oncogene amplification testing in histo-pathological routine images of breast and gastric cancer diagnosticsCode0
Can we learn better with hard samples?Code0
Understanding Intrinsic Robustness Using Label UncertaintyCode0
An Interaction-based Convolutional Neural Network (ICNN) Towards Better Understanding of COVID-19 X-ray ImagesCode0
Inception-inspired LSTM for Next-frame Video PredictionCode0
Improvising the Learning of Neural Networks on Hyperspherical ManifoldCode0
Can Score-Based Generative Modeling Effectively Handle Medical Image Classification?Code0
An Information-Geometric Distance on the Space of TasksCode0
Image Data Augmentation Approaches: A Comprehensive Survey and Future directionsCode0
Revisiting 16-bit Neural Network Training: A Practical Approach for Resource-Limited LearningCode0
Improving the repeatability of deep learning models with Monte Carlo dropoutCode0
An Inertial Newton Algorithm for Deep LearningCode0
Improving the Gating Mechanism of Recurrent Neural NetworksCode0
A Downsampled Variant of ImageNet as an Alternative to the CIFAR datasetsCode0
An In-Depth Analysis of Adversarial Discriminative Domain Adaptation for Digit ClassificationCode0
Can a Confident Prior Replace a Cold Posterior?Code0
3D Wavelet Convolutions with Extended Receptive Fields for Hyperspectral Image ClassificationCode0
Improving the Efficiency of Human-in-the-Loop Systems: Adding Artificial to Human ExpertsCode0
Improving the trustworthiness of image classification models by utilizing bounding-box annotationsCode0
CAMP: Continuous and Adaptive Learning Model in PathologyCode0
An Improvement of Data Classification Using Random Multimodel Deep Learning (RMDL)Code0
Improving Shift Invariance in Convolutional Neural Networks with Translation Invariant Polyphase SamplingCode0
CAM-Based Methods Can See through WallsCode0
Improving robustness to corruptions with multiplicative weight perturbationsCode0
Improving singing voice separation with the Wave-U-Net using Minimum Hyperspherical EnergyCode0
Improving Transferability of Adversarial Examples with Input DiversityCode0
Calibration of Deep Probabilistic Models with Decoupled Bayesian Neural NetworksCode0
An Image Patch is a Wave: Phase-Aware Vision MLPCode0
Adopting Two Supervisors for Efficient Use of Large-Scale Remote Deep Neural NetworksCode0
Improving Nonlinear Projection Heads using Pretrained Autoencoder EmbeddingsCode0
Improving Pairwise Ranking for Multi-label Image ClassificationCode0
Calibrating Deep Convolutional Gaussian ProcessesCode0
Calibrate to InterpretCode0
Angle based dynamic learning rate for gradient descentCode0
Calibrated Selective ClassificationCode0
Improving model calibration with accuracy versus uncertainty optimizationCode0
Improving Neural Architecture Search Image Classifiers via Ensemble LearningCode0
Improving Pre-Trained Weights Through Meta-Heuristics Fine-TuningCode0
Show:102550
← PrevPage 54 of 209Next →

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