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 5751–5800 of 10420 papers

TitleStatusHype
TokenLearner: What Can 8 Learned Tokens Do for Images and Videos?Code1
Communication Efficient SGD via Gradient Sampling With Bayes Prior—0
T-vMF Similarity for Regularizing Intra-Class Feature DistributionCode1
Spatial Assembly Networks for Image Representation Learning—0
Quality-Agnostic Image Recognition via Invertible DecoderCode0
CapsuleRRT: Relationships-Aware Regression Tracking via Capsules—0
Distribution-Aware Adaptive Multi-Bit Quantization—0
Boosting Ensemble Accuracy by Revisiting Ensemble Diversity MetricsCode0
MaxUp: Lightweight Adversarial Training With Data Augmentation Improves Neural Network Training—0
Hilbert Sinkhorn Divergence for Optimal Transport—0
Self-Supervised Wasserstein Pseudo-Labeling for Semi-Supervised Image Classification—0
Teacher's pet: understanding and mitigating biases in distillation—0
Exploring Vision Transformers for Fine-grained ClassificationCode1
QFCNN: Quantum Fourier Convolutional Neural Network—0
Informative Class Activation Maps—0
Practical Transferability Estimation for Image Classification Tasks—0
Cross Modality Knowledge Distillation for Multi-Modal Aerial View Object ClassificationCode0
Certified robustness against adversarial patch attacks via randomized cropping—0
Defending Adversaries Using Unsupervised Feature Clustering VAE—0
Equivariance-bridged SO(2)-Invariant Representation Learning using Graph Convolutional NetworkCode1
Effective Model Sparsification by Scheduled Grow-and-Prune MethodsCode0
Residual Error: a New Performance Measure for Adversarial Robustness—0
Quantized Neural Networks via -1, +1 Encoding Decomposition and AccelerationCode0
Light Lies: Optical Adversarial Attack—0
How to train your ViT? Data, Augmentation, and Regularization in Vision TransformersCode1
Contrastive Learning of Generalized Game RepresentationsCode1
Deep reinforcement learning with automated label extraction from clinical reports accurately classifies 3D MRI brain volumes—0
Evaluating the Robustness of Bayesian Neural Networks Against Different Types of Attacks—0
MetaBalance: High-Performance Neural Networks for Class-Imbalanced Data—0
Deep Subdomain Adaptation Network for Image ClassificationCode1
XCiT: Cross-Covariance Image TransformersCode3
Multi-Label Learning from Single Positive LabelsCode1
ShuffleBlock: Shuffle to Regularize Deep Convolutional Neural Networks—0
Effective Evaluation of Deep Active Learning on Image Classification Tasks—0
Federated Semi-supervised Medical Image Classification via Inter-client Relation MatchingCode1
Bridging Multi-Task Learning and Meta-Learning: Towards Efficient Training and Effective AdaptationCode1
Disentangling Semantic-to-visual Confusion for Zero-shot LearningCode0
DeepSplit: Scalable Verification of Deep Neural Networks via Operator SplittingCode0
Input Invex Neural NetworkCode0
ParticleAugment: Sampling-Based Data Augmentation—0
Positional Contrastive Learning for Volumetric Medical Image SegmentationCode1
Robust Training in High Dimensions via Block Coordinate Geometric Median DescentCode0
Structured DropConnect for Uncertainty Inference in Image ClassificationCode0
Test Sample Accuracy Scales with Training Sample Density in Neural NetworksCode0
Zero-sample surface defect detection and classification based on semantic feedback neural network—0
Revisiting the Calibration of Modern Neural NetworksCode0
BEiT: BERT Pre-Training of Image TransformersCode2
A Lightweight ReLU-Based Feature Fusion for Aerial Scene Classification—0
SAR Image Classification Based on Spiking Neural Network through Spike-Time Dependent Plasticity and Gradient DescentCode1
Contextualizing Meta-Learning via Learning to DecomposeCode0
Show:102550
← PrevPage 116 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
5DaViT-HTop 1 Accuracy90.2—Unverified
6Meta Pseudo Labels (EfficientNet-L2)Top 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
10Meta Pseudo Labels (EfficientNet-B6-Wide)Top 1 Accuracy90—Unverified