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 9511000 of 10419 papers

TitleStatusHype
A Conservative Approach for Unbiased Learning on Unknown BiasesCode1
Convolution-enhanced Evolving Attention NetworksCode1
Heavy Ball Neural Ordinary Differential EquationsCode1
Heteroskedastic and Imbalanced Deep Learning with Adaptive RegularizationCode1
AASAE: Augmentation-Augmented Stochastic AutoencodersCode1
Convolutional Sequence to Sequence LearningCode1
Babel-ImageNet: Massively Multilingual Evaluation of Vision-and-Language RepresentationsCode1
Convolutional Xformers for VisionCode1
A Rainbow in Deep Network Black BoxesCode1
Adversarial Robustness on In- and Out-Distribution Improves ExplainabilityCode1
CrossFormer: A Versatile Vision Transformer Hinging on Cross-scale AttentionCode1
CycleMLP: A MLP-like Architecture for Dense PredictionCode1
Balanced-MixUp for Highly Imbalanced Medical Image ClassificationCode1
HMIL: Hierarchical Multi-Instance Learning for Fine-Grained Whole Slide Image ClassificationCode1
DiG-IN: Diffusion Guidance for Investigating Networks - Uncovering Classifier Differences Neuron Visualisations and Visual Counterfactual ExplanationsCode1
How Does Pruning Impact Long-Tailed Multi-Label Medical Image Classifiers?Code1
Arch-Net: Model Distillation for Architecture Agnostic Model DeploymentCode1
Counterfactual Visual ExplanationsCode1
CosPGD: an efficient white-box adversarial attack for pixel-wise prediction tasksCode1
Shallow-Deep Networks: Understanding and Mitigating Network OverthinkingCode1
Co-Tuning for Transfer LearningCode1
Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy LabelsCode1
Counterfactual Generative NetworksCode1
HRN: A Holistic Approach to One Class LearningCode1
Are Natural Domain Foundation Models Useful for Medical Image Classification?Code1
Hyperbolic Contrastive Learning for Visual Representations beyond ObjectsCode1
Hyperbolic Image EmbeddingsCode1
Hyperbolic Image-Text RepresentationsCode1
COVID-CXNet: Detecting COVID-19 in Frontal Chest X-ray Images using Deep LearningCode1
CoV-TI-Net: Transferred Initialization with Modified End Layer for COVID-19 DiagnosisCode1
Hyperspectral Image Classification-Traditional to Deep Models: A Survey for Future ProspectsCode1
Are These Birds Similar: Learning Branched Networks for Fine-grained RepresentationsCode1
CPrune: Compiler-Informed Model Pruning for Efficient Target-Aware DNN ExecutionCode1
All-in-One Image Coding for Joint Human-Machine Vision with Multi-Path AggregationCode1
CrAM: A Compression-Aware MinimizerCode1
iDAT: inverse Distillation Adapter-TuningCode1
Image Classification by Reinforcement Learning with Two-State Q-LearningCode1
ChimeraMix: Image Classification on Small Datasets via Masked Feature MixingCode1
Cross-Domain Ensemble Distillation for Domain GeneralizationCode1
Can We Talk Models Into Seeing the World Differently?Code1
Backdoor Attacks on Crowd CountingCode1
BAGAN: Data Augmentation with Balancing GANCode1
Cross-modal Adversarial ReprogrammingCode1
Cross-Layer Retrospective Retrieving via Layer AttentionCode1
Dilated convolution with learnable spacingsCode1
Cross-modulated Few-shot Image Generation for Colorectal Tissue ClassificationCode1
A Fast 3D CNN for Hyperspectral Image ClassificationCode1
ImageNet Large Scale Visual Recognition ChallengeCode1
Dirichlet-based Uncertainty Calibration for Active Domain AdaptationCode1
Disentangled Feature Representation for Few-shot Image ClassificationCode1
Show:102550
← PrevPage 20 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
5DaViT-HTop 1 Accuracy90.2Unverified
6Meta Pseudo Labels (EfficientNet-L2)Top 1 Accuracy90.2Unverified
7SwinV2-GTop 1 Accuracy90.17Unverified
8MAWS (ViT-6.5B)Top 1 Accuracy90.1Unverified
9Florence-CoSwin-HTop 1 Accuracy90.05Unverified
10Meta Pseudo Labels (EfficientNet-B6-Wide)Top 1 Accuracy90Unverified