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 42014250 of 10420 papers

TitleStatusHype
Test-time Adaptation with Calibration of Medical Image Classification Nets for Label Distribution ShiftCode1
Learning Cross-Image Object Semantic Relation in Transformer for Few-Shot Fine-Grained Image ClassificationCode1
Unsupervised Cross-Domain Feature Extraction for Single Blood Cell Image ClassificationCode0
On Leave-One-Out Conditional Mutual Information For Generalization0
BadHash: Invisible Backdoor Attacks against Deep Hashing with Clean LabelCode1
Graph Information Aggregation Cross-Domain Few-Shot Learning for Hyperspectral Image ClassificationCode1
Improving Ensemble Distillation With Weight Averaging and Diversifying PerturbationCode0
Learning Iterative Reasoning through Energy MinimizationCode1
Shifts 2.0: Extending The Dataset of Real Distributional ShiftsCode2
Revisiting Label Smoothing and Knowledge Distillation Compatibility: What was Missing?Code1
FedIIC: Towards Robust Federated Learning for Class-Imbalanced Medical Image ClassificationCode1
ZoDIAC: Zoneout Dropout Injection Attention CalculationCode0
RevBiFPN: The Fully Reversible Bidirectional Feature Pyramid NetworkCode1
Robustifying Vision Transformer without Retraining from Scratch by Test-Time Class-Conditional Feature AlignmentCode1
Continual Learning with Transformers for Image Classification0
Improved Text Classification via Test-Time Augmentation0
Compressing Features for Learning with Noisy LabelsCode1
Thermodynamics-inspired Explanations of Artificial IntelligenceCode1
Benchopt: Reproducible, efficient and collaborative optimization benchmarksCode4
Kernel Attention Transformer (KAT) for Histopathology Whole Slide Image ClassificationCode1
Unsupervised Domain Adaptation Using Feature Disentanglement And GCNs For Medical Image Classification0
Self-supervised Learning in Remote Sensing: A ReviewCode1
Multi-view Feature Augmentation with Adaptive Class Activation Mapping0
Representative Teacher Keys for Knowledge Distillation Model Compression Based on Attention Mechanism for Image Classification0
Inverted Semantic-Index for Image Retrieval0
p-Meta: Towards On-device Deep Model Adaptation0
PLATON: Pruning Large Transformer Models with Upper Confidence Bound of Weight ImportanceCode1
FLVoogd: Robust And Privacy Preserving Federated Learning0
Evolution of Activation Functions for Deep Learning-Based Image Classification0
Multitask vocal burst modeling with ResNets and pre-trained paralinguistic Conformers0
Self Supervised Learning for Few Shot Hyperspectral Image Classification0
FEATHERS: Federated Architecture and Hyperparameter Search0
Revisiting Orthogonality Regularization: A Study for Convolutional Neural Networks in Image ClassificationCode0
Open-source FPGA-ML codesign for the MLPerf Tiny BenchmarkCode0
A novel adversarial learning strategy for medical image classification0
Learning Viewpoint-Agnostic Visual Representations by Recovering Tokens in 3D SpaceCode1
Toward Clinically Assisted Colorectal Polyp Recognition via Structured Cross-modal Representation ConsistencyCode1
A Model-Agnostic SAT-based Approach for Symbolic Explanation Enumeration0
Single-phase deep learning in cortico-cortical networksCode0
Few-Shot Non-Parametric Learning with Deep Latent Variable Model0
Feature Re-calibration based Multiple Instance Learning for Whole Slide Image ClassificationCode1
Coupling Visual Semantics of Artificial Neural Networks and Human Brain Function via Synchronized Activations0
Fighting Fire with Fire: Avoiding DNN Shortcuts through Priming0
How to Combine Variational Bayesian Networks in Federated LearningCode1
ROSE: A RObust and SEcure DNN Watermarking0
Vicinity Vision TransformerCode1
EdgeNeXt: Efficiently Amalgamated CNN-Transformer Architecture for Mobile Vision ApplicationsCode2
TCJA-SNN: Temporal-Channel Joint Attention for Spiking Neural NetworksCode1
VulCNN: An Image-inspired Scalable Vulnerability Detection SystemCode1
Remote Sensing Image Classification using Transfer Learning and Attention Based Deep Neural Network0
Show:102550
← PrevPage 85 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