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 4651–4700 of 10420 papers

TitleStatusHype
ViM: Out-Of-Distribution with Virtual-logit MatchingCode1
Image Classification on Accelerated Neural Networks—0
Towards Self-Supervised Gaze Estimation—0
Test-time Adaptation with Slot-Centric ModelsCode1
CoWs on Pasture: Baselines and Benchmarks for Language-Driven Zero-Shot Object NavigationCode1
Vision Transformer with Convolutions Architecture Search—0
CRISPnet: Color Rendition ISP Net—0
Over-parameterization: A Necessary Condition for Models that Extrapolate—0
Deep Learning Generalization, Extrapolation, and Over-parameterization—0
Incremental Few-Shot Learning via Implanting and Compressing—0
Three things everyone should know about Vision TransformersCode0
Identifying Transients in the Dark Energy Survey using Convolutional Neural NetworksCode0
Do Deep Networks Transfer Invariances Across Classes?Code1
DocXClassifier: High Performance Explainable Deep Network for Document Image ClassificationCode1
An Interactive Explanatory AI System for Industrial Quality Control—0
Inducing Neural Collapse in Imbalanced Learning: Do We Really Need a Learnable Classifier at the End of Deep Neural Network?Code1
Transframer: Arbitrary Frame Prediction with Generative Models—0
DATA: Domain-Aware and Task-Aware Self-supervised LearningCode1
Confidence Dimension for Deep Learning based on Hoeffding Inequality and Relative Evaluation—0
A New Quantum CNN Model for Image Classification—0
A Continual Learning Framework for Adaptive Defect Classification and Inspection—0
Open Set Recognition using Vision Transformer with an Additional Detection HeadCode1
Meta-Learning of NAS for Few-shot Learning in Medical Image Applications—0
Is it all a cluster game? -- Exploring Out-of-Distribution Detection based on Clustering in the Embedding Space—0
UnseenNet: Fast Training Detector for Any Unseen ConceptCode0
Learning to Generate Synthetic Training Data using Gradient Matching and Implicit DifferentiationCode0
Decoupled Knowledge DistillationCode2
2-speed network ensemble for efficient classification of incremental land-use/land-cover satellite image chips—0
Towards understanding deep learning with the natural clustering prior—0
InsCon:Instance Consistency Feature Representation via Self-Supervised Learning—0
Scalable Penalized Regression for Noise Detection in Learning with Noisy LabelsCode1
Bamboo: Building Mega-Scale Vision Dataset Continually with Human-Machine SynergyCode1
One Network Doesn't Rule Them All: Moving Beyond Handcrafted Architectures in Self-Supervised Learning—0
Generalized but not Robust? Comparing the Effects of Data Modification Methods on Out-of-Domain Generalization and Adversarial Robustness—0
Meta Ordinal Regression Forest for Medical Image Classification with Ordinal Labels—0
Energy-Latency Attacks via Sponge PoisoningCode1
On the Calibration of Pre-trained Language Models using Mixup Guided by Area Under the Margin and Saliency—0
UniVIP: A Unified Framework for Self-Supervised Visual Pre-training—0
Cross-View-Prediction: Exploring Contrastive Feature for Hyperspectral Image Classification—0
Scaling the Wild: Decentralizing Hogwild!-style Shared-memory SGDCode0
Scaling Up Your Kernels to 31x31: Revisiting Large Kernel Design in CNNsCode2
GSDA: Generative Adversarial Network-based Semi-Supervised Data Augmentation for Ultrasound Image Classification—0
Learning from Attacks: Attacking Variational Autoencoder for Improving Image Classification—0
Spatial Consistency Loss for Training Multi-Label Classifiers from Single-Label Annotations—0
Sparse Subspace Clustering for Concept Discovery (SSCCD)—0
QDrop: Randomly Dropping Quantization for Extremely Low-bit Post-Training QuantizationCode2
Deep AutoAugmentCode1
Active Token MixerCode1
Deep Multimodal Guidance for Medical Image ClassificationCode1
Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference timeCode2
Show:102550
← PrevPage 94 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