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

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 4801–4850 of 10420 papers

TitleStatusHype
Feature-level augmentation to improve robustness of deep neural networks to affine transformations—0
Multi-relation Message Passing for Multi-label Text ClassificationCode0
Spherical Transformer—0
Class Distance Weighted Cross-Entropy Loss for Ulcerative Colitis Severity EstimationCode1
Image Difference Captioning with Pre-training and Contrastive LearningCode1
L2B: Learning to Bootstrap Robust Models for Combating Label NoiseCode1
Improving greedy core-set configurations for active learning with uncertainty-scaled distances—0
Methods for the frugal labeler: Multi-class semantic segmentation on heterogeneous labelsCode0
TransformNet: Self-supervised representation learning through predicting geometric transformationsCode0
Comparative Study Between Distance Measures On Supervised Optimum-Path Forest ClassificationCode0
Uncertainty Modeling for Out-of-Distribution GeneralizationCode1
If a Human Can See It, So Should Your System: Reliability Requirements for Machine Vision Components—0
Equivariance versus Augmentation for Spherical ImagesCode0
Modeling Structure with Undirected Neural NetworksCode0
Multi-Label Classification of Thoracic Diseases using Dense Convolutional Network on Chest RadiographsCode0
Data Consistency for Weakly Supervised Learning—0
DALL-Eval: Probing the Reasoning Skills and Social Biases of Text-to-Image Generation ModelsCode3
OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning FrameworkCode0
Diversify and Disambiguate: Learning From Underspecified DataCode1
Simple Control Baselines for Evaluating Transfer Learning—0
Dataset Condensation with Contrastive SignalsCode1
data2vec: A General Framework for Self-supervised Learning in Speech, Vision and LanguageCode1
Transformers in Self-Supervised Monocular Depth Estimation with Unknown Camera IntrinsicsCode1
Corrupted Image Modeling for Self-Supervised Visual Pre-Training—0
No Parameters Left Behind: Sensitivity Guided Adaptive Learning Rate for Training Large Transformer ModelsCode1
Decision boundaries and convex hulls in the feature space that deep learning functions learn from images—0
Learning with Neighbor Consistency for Noisy Labels—0
Choosing an Appropriate Platform and Workflow for Processing Camera Trap Data using Artificial Intelligence—0
Backpropagation Neural TreeCode0
Best Practices and Scoring System on Reviewing A.I. based Medical Imaging Papers: Part 1 Classification—0
Learning strides in convolutional neural networksCode1
FORML: Learning to Reweight Data for Fairness—0
Fast Convex Optimization for Two-Layer ReLU Networks: Equivalent Model Classes and Cone DecompositionsCode1
VOS: Learning What You Don't Know by Virtual Outlier SynthesisCode2
Federated Active Learning (F-AL): an Efficient Annotation Strategy for Federated Learning—0
Classification of Skin Cancer Images using Convolutional Neural Networks—0
Access Control of Object Detection Models Using Encrypted Feature Maps—0
When Do Flat Minima Optimizers Work?Code1
Fortuitous Forgetting in Connectionist NetworksCode1
Rate Coding or Direct Coding: Which One is Better for Accurate, Robust, and Energy-efficient Spiking Neural Networks?Code1
AntidoteRT: Run-time Detection and Correction of Poison Attacks on Neural NetworksCode0
Adversarial Robustness in Deep Learning: Attacks on Fragile Neurons—0
NAS-Bench-Suite: NAS Evaluation is (Now) Surprisingly Easy—0
UQGAN: A Unified Model for Uncertainty Quantification of Deep Classifiers trained via Conditional GANsCode1
Plug-In Inversion: Model-Agnostic Inversion for Vision with Data AugmentationsCode1
Volley Revolver: A Novel Matrix-Encoding Method for Privacy-Preserving Neural Networks (Inference)Code0
Image Classification using Graph Neural Network and Multiscale Wavelet Superpixels—0
Towards Robust Deep Active Learning for Scientific Computing—0
Low-rank features based double transformation matrices learning for image classification—0
DynaMixer: A Vision MLP Architecture with Dynamic MixingCode1
Show:102550
← PrevPage 97 of 209Next →
All datasetsImageNetCIFAR-10CIFAR-100STL-10ObjectNetMNISTSVHNiNaturalist 2018ImageNet ReaLFlowers-102Clothing1Mmini WebVision 1.0

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1CoCa (finetuned)Top 1 Accuracy91—Unverified
2Model soups (BASIC-L)Top 1 Accuracy90.98—Unverified
3Model soups (ViT-G/14)Top 1 Accuracy90.94—Unverified
4DaViT-GTop 1 Accuracy90.4—Unverified
5Meta Pseudo Labels (EfficientNet-L2)Top 1 Accuracy90.2—Unverified
6DaViT-HTop 1 Accuracy90.2—Unverified
7SwinV2-GTop 1 Accuracy90.17—Unverified
8MAWS (ViT-6.5B)Top 1 Accuracy90.1—Unverified
9Florence-CoSwin-HTop 1 Accuracy90.05—Unverified
10RevCol-HTop 1 Accuracy90—Unverified