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 8001–8050 of 10420 papers

TitleStatusHype
Deep Axial Hypercomplex Networks—0
ResNetX: a more disordered and deeper network architecture—0
Resolution-Based Distillation for Efficient Histology Image Classification—0
Improve Unsupervised Domain Adaptation with Mixup Training—0
REFT: Resource-Efficient Federated Training Framework for Heterogeneous and Resource-Constrained Environments—0
Resource Efficient Neural Networks Using Hessian Based Pruning—0
Deep Autoencoder Model Construction Based on Pytorch—0
Improvement Strategies for Few-Shot Learning in OCT Image Classification of Rare Retinal Diseases—0
Improvement of image classification by multiple optical scattering—0
Deep AUC Maximization for Medical Image Classification: Challenges and Opportunities—0
Restricted Boltzmann Machines for galaxy morphology classification with a quantum annealer—0
RE-Tagger: A light-weight Real-Estate Image Classifier—0
RetailKLIP : Finetuning OpenCLIP backbone using metric learning on a single GPU for Zero-shot retail product image classification—0
Retaining Knowledge and Enhancing Long-Text Representations in CLIP through Dual-Teacher Distillation—0
Automatic Radiology Report Generation based on Multi-view Image Fusion and Medical Concept Enrichment—0
Rethinking and Improving Relative Position Encoding for Vision Transformer—0
Identify ambiguous tasks combining crowdsourced labels by weighting Areas Under the Margin—0
Improved Training Speed, Accuracy, and Data Utilization via Loss Function Optimization—0
Deep Attributes from Context-Aware Regional Neural Codes—0
Improved Trainable Calibration Method for Neural Networks on Medical Imaging Classification—0
Improved texture image classification through the use of a corrosion-inspired cellular automaton—0
Rethinking Crowdsourcing Annotation: Partial Annotation with Salient Labels for Multi-Label Image Classification—0
Deep Algorithmic Question Answering: Towards a Compositionally Hybrid AI for Algorithmic Reasoning—0
Improved Text Classification via Test-Time Augmentation—0
Improved Robustness of Vision Transformer via PreLayerNorm in Patch Embedding—0
DeepAGREL: Biologically plausible deep learning via direct reinforcement—0
Rethinking Foundation Models for Medical Image Classification through a Benchmark Study on MedMNIST—0
Rethinking Generative Zero-Shot Learning: An Ensemble Learning Perspective for Recognising Visual Patches—0
Rethinking Hard-Parameter Sharing in Multi-Domain Learning—0
Rethinking Image Editing Detection in the Era of Generative AI Revolution—0
Automatic estimation of heading date of paddy rice using deep learning—0
A Local Detection Approach for Named Entity Recognition and Mention Detection—0
Between Progress and Potential Impact of AI: the Neglected Dimensions—0
Deep Adaptive Semantic Logic (DASL): Compiling Declarative Knowledge into Deep Neural Networks—0
Automatic Error Detection in Integrated Circuits Image Segmentation: A Data-driven Approach—0
PAWS-VMK: A Unified Approach To Semi-Supervised Learning And Out-of-Distribution Detection—0
Frustratingly Easy Uncertainty Estimation for Distribution Shift—0
Improved OOD Generalization via Adversarial Training and Pre-training—0
Deep Active Learning in the Presence of Label Noise: A Survey—0
Automatic discovery of discriminative parts as a quadratic assignment problem—0
Improved Multi-Source Domain Adaptation by Preservation of Factors—0
Rethinking Persistent Homology for Visual Recognition—0
Rethinking Pseudo Labels for Semi-Supervised Object Detection—0
Rethinking Query, Key, and Value Embedding in Vision Transformer under Tiny Model Constraints—0
Deep Active Learning in the Open World—0
Rethinking Semi-Supervised Federated Learning: How to co-train fully-labeled and fully-unlabeled client imaging data—0
Improved Mix-up with KL-Entropy for Learning From Noisy Labels—0
Rethinking Skip Connection with Layer Normalization—0
Does Deep Active Learning Work in the Wild?—0
Improved Image Classification with Token Fusion—0
Show:102550
← PrevPage 161 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