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 10511100 of 10419 papers

TitleStatusHype
Compressing Features for Learning with Noisy LabelsCode1
Thermodynamics-inspired Explanations of Artificial IntelligenceCode1
Kernel Attention Transformer (KAT) for Histopathology Whole Slide Image ClassificationCode1
Self-supervised Learning in Remote Sensing: A ReviewCode1
PLATON: Pruning Large Transformer Models with Upper Confidence Bound of Weight ImportanceCode1
Learning Viewpoint-Agnostic Visual Representations by Recovering Tokens in 3D SpaceCode1
Toward Clinically Assisted Colorectal Polyp Recognition via Structured Cross-modal Representation ConsistencyCode1
How to Combine Variational Bayesian Networks in Federated LearningCode1
Feature Re-calibration based Multiple Instance Learning for Whole Slide Image ClassificationCode1
TCJA-SNN: Temporal-Channel Joint Attention for Spiking Neural NetworksCode1
Vicinity Vision TransformerCode1
VulCNN: An Image-inspired Scalable Vulnerability Detection SystemCode1
Contextual Squeeze-and-Excitation for Efficient Few-Shot Image ClassificationCode1
EATFormer: Improving Vision Transformer Inspired by Evolutionary AlgorithmCode1
FiT: Parameter Efficient Few-shot Transfer Learning for Personalized and Federated Image ClassificationCode1
DGMIL: Distribution Guided Multiple Instance Learning for Whole Slide Image ClassificationCode1
Simple and Efficient Architectures for Semantic SegmentationCode1
Channel Importance Matters in Few-Shot Image ClassificationCode1
PRANC: Pseudo RAndom Networks for Compacting deep modelsCode1
Boosting the Adversarial Transferability of Surrogate Models with Dark KnowledgeCode1
SP-ViT: Learning 2D Spatial Priors for Vision TransformersCode1
Differentiable Top-k Classification LearningCode1
Morphence-2.0: Evasion-Resilient Moving Target Defense Powered by Out-of-Distribution DetectionCode1
Masked Frequency Modeling for Self-Supervised Visual Pre-TrainingCode1
Peripheral Vision TransformerCode1
Evaluating histopathology transfer learning with ChampKitCode1
Masked Autoencoders are Robust Data AugmentorsCode1
Disentangled Ontology Embedding for Zero-shot LearningCode1
S3Net: Spectral–Spatial Siamese Network for Few-Shot Hyperspectral Image ClassificationCode1
FixCaps: An Improved Capsules Network for Diagnosis of Skin CancerCode1
Localizing Semantic Patches for Accelerating Image ClassificationCode1
Masked Unsupervised Self-training for Label-free Image ClassificationCode1
Tackling covariate shift with node-based Bayesian neural networksCode1
JigsawHSI: a network for Hyperspectral Image classificationCode1
Optimizing Relevance Maps of Vision Transformers Improves RobustnessCode1
A memory-efficient neural ODE framework based on high-level adjoint differentiationCode1
Efficient Self-supervised Vision Pretraining with Local Masked ReconstructionCode1
CLIP4IDC: CLIP for Image Difference CaptioningCode1
Going Beyond One-Hot Encoding in Classification: Can Human Uncertainty Improve Model Performance?Code1
Revisiting the Importance of Amplifying Bias for DebiasingCode1
A Closer Look at Self-Supervised Lightweight Vision TransformersCode1
WaveMix: A Resource-efficient Neural Network for Image AnalysisCode1
Failure Detection in Medical Image Classification: A Reality Check and Benchmarking TestbedCode1
DLTTA: Dynamic Learning Rate for Test-time Adaptation on Cross-domain Medical ImagesCode1
Dual-Perspective Semantic-Aware Representation Blending for Multi-Label Image Recognition with Partial LabelsCode1
Trainable Weight Averaging: A General Approach for Subspace TrainingCode1
MixMAE: Mixed and Masked Autoencoder for Efficient Pretraining of Hierarchical Vision TransformersCode1
Boosting Multi-Label Image Classification with Complementary Parallel Self-DistillationCode1
Knowledge Distillation from A Stronger TeacherCode1
Vision Transformers in 2022: An Update on Tiny ImageNetCode1
Show:102550
← PrevPage 22 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