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 651700 of 10419 papers

TitleStatusHype
How Does Pruning Impact Long-Tailed Multi-Label Medical Image Classifiers?Code1
Vision-Language Dataset DistillationCode1
AdvCLIP: Downstream-agnostic Adversarial Examples in Multimodal Contrastive LearningCode1
Towards Open-Set Test-Time Adaptation Utilizing the Wisdom of Crowds in Entropy MinimizationCode1
Probabilistic MIMO U-Net: Efficient and Accurate Uncertainty Estimation for Pixel-wise RegressionCode1
SimMatchV2: Semi-Supervised Learning with Graph ConsistencyCode1
Gated Attention Coding for Training High-performance and Efficient Spiking Neural NetworksCode1
Fine-Grained Self-Supervised Learning with Jigsaw Puzzles for Medical Image ClassificationCode1
Robust Asymmetric Loss for Multi-Label Long-Tailed LearningCode1
Spatial Gated Multi-Layer Perceptron for Land Use and Land Cover MappingCode1
Which Tokens to Use? Investigating Token Reduction in Vision TransformersCode1
Improving Medical Image Classification in Noisy Labels Using Only Self-supervised PretrainingCode1
CheXFusion: Effective Fusion of Multi-View Features using Transformers for Long-Tailed Chest X-Ray ClassificationCode1
AFN: Adaptive Fusion Normalization via an Encoder-Decoder FrameworkCode1
NP-SemiSeg: When Neural Processes meet Semi-Supervised Semantic SegmentationCode1
ReCLIP: Refine Contrastive Language Image Pre-Training with Source Free Domain AdaptationCode1
URET: Universal Robustness Evaluation Toolkit (for Evasion)Code1
VisAlign: Dataset for Measuring the Degree of Alignment between AI and Humans in Visual PerceptionCode1
A Novel Convolutional Neural Network Architecture with a Continuous SymmetryCode1
Dynamic Token Pruning in Plain Vision Transformers for Semantic SegmentationCode1
PerceptionCLIP: Visual Classification by Inferring and Conditioning on ContextsCode1
NormKD: Normalized Logits for Knowledge DistillationCode1
ViT2EEG: Leveraging Hybrid Pretrained Vision Transformers for EEG DataCode1
CDUL: CLIP-Driven Unsupervised Learning for Multi-Label Image ClassificationCode1
Task-Oriented Channel Attention for Fine-Grained Few-Shot ClassificationCode1
Multiple Instance Learning Framework with Masked Hard Instance Mining for Whole Slide Image ClassificationCode1
Quantum-limited stochastic optical neural networks operating at a few quanta per activationCode1
Text-guided Foundation Model Adaptation for Pathological Image ClassificationCode1
Federated Model Aggregation via Self-Supervised Priors for Highly Imbalanced Medical Image ClassificationCode1
PromptStyler: Prompt-driven Style Generation for Source-free Domain GeneralizationCode1
Understanding Silent Failures in Medical Image ClassificationCode1
Why Is Prompt Tuning for Vision-Language Models Robust to Noisy Labels?Code1
GEM: Boost Simple Network for Glass Surface Segmentation via Vision Foundation ModelsCode1
CLR: Channel-wise Lightweight Reprogramming for Continual LearningCode1
Tuning Pre-trained Model via Moment ProbingCode1
GIST: Generating Image-Specific Text for Fine-grained Object ClassificationCode1
FedSoup: Improving Generalization and Personalization in Federated Learning via Selective Model InterpolationCode1
Semantic-Aware Dual Contrastive Learning for Multi-label Image ClassificationCode1
Interpreting and Correcting Medical Image Classification with PIP-NetCode1
What do neural networks learn in image classification? A frequency shortcut perspectiveCode1
Systematic comparison of semi-supervised and self-supervised learning for medical image classificationCode1
Bridging the Gap: Multi-Level Cross-Modality Joint Alignment for Visible-Infrared Person Re-IdentificationCode1
M-FLAG: Medical Vision-Language Pre-training with Frozen Language Models and Latent Space Geometry OptimizationCode1
Diffusion Models Beat GANs on Image ClassificationCode1
CellGAN: Conditional Cervical Cell Synthesis for Augmenting Cytopathological Image ClassificationCode1
Revisiting Computer-Aided Tuberculosis DiagnosisCode1
Distilling Large Vision-Language Model with Out-of-Distribution GeneralizabilityCode1
Benchmarking Test-Time Adaptation against Distribution Shifts in Image ClassificationCode1
Rethinking Multiple Instance Learning for Whole Slide Image Classification: A Good Instance Classifier is All You NeedCode1
FedDefender: Backdoor Attack Defense in Federated LearningCode1
Show:102550
← PrevPage 14 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