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 20012050 of 10419 papers

TitleStatusHype
The Information Pathways Hypothesis: Transformers are Dynamic Self-EnsemblesCode1
The Large Labelled Logo Dataset (L3D): A Multipurpose and Hand-Labelled Continuously Growing DatasetCode1
The Majority Can Help The Minority: Context-rich Minority Oversampling for Long-tailed ClassificationCode1
The Need for Speed: Pruning Transformers with One RecipeCode1
The Reversible Residual Network: Backpropagation Without Storing ActivationsCode1
The Rise of AI Language Pathologists: Exploring Two-level Prompt Learning for Few-shot Weakly-supervised Whole Slide Image ClassificationCode1
DGMIL: Distribution Guided Multiple Instance Learning for Whole Slide Image ClassificationCode1
A General Framework For Detecting Anomalous Inputs to DNN ClassifiersCode1
TiC: Exploring Vision Transformer in ConvolutionCode1
Time Series as Images: Vision Transformer for Irregularly Sampled Time SeriesCode1
Complementary-Label Learning for Arbitrary Losses and ModelsCode1
Token Cropr: Faster ViTs for Quite a Few TasksCode1
All Tokens Matter: Token Labeling for Training Better Vision TransformersCode1
TokenLearner: What Can 8 Learned Tokens Do for Images and Videos?Code1
DetCo: Unsupervised Contrastive Learning for Object DetectionCode1
Detecting AutoAttack Perturbations in the Frequency DomainCode1
Total Variation Optimization Layers for Computer VisionCode1
Toward Clinically Assisted Colorectal Polyp Recognition via Structured Cross-modal Representation ConsistencyCode1
Counterfactual Explanations for Medical Image Classification and Regression using Diffusion AutoencoderCode1
Towards Accurate Post-training Network Quantization via Bit-Split and StitchingCode1
Compositional Explanations of NeuronsCode1
Towards a Unified View on Visual Parameter-Efficient Transfer LearningCode1
ACPL: Anti-curriculum Pseudo-labelling for Semi-supervised Medical Image ClassificationCode1
Towards Effective Visual Representations for Partial-Label LearningCode1
Towards Evaluating Explanations of Vision Transformers for Medical ImagingCode1
Towards Feature Space Adversarial AttackCode1
Towards General and Efficient Active LearningCode1
Compounding the Performance Improvements of Assembled Techniques in a Convolutional Neural NetworkCode1
Towards Interpretable Radiology Report Generation via Concept Bottlenecks using a Multi-Agentic RAGCode1
Towards Interpretable Semantic Segmentation via Gradient-weighted Class Activation MappingCode1
Towards Robust and Reproducible Active Learning Using Neural NetworksCode1
Towards Robust Classification Model by Counterfactual and Invariant Data GenerationCode1
Concurrent Spatial and Channel Squeeze & Excitation in Fully Convolutional NetworksCode1
SSIVD-Net: A Novel Salient Super Image Classification & Detection Technique for Weaponized ViolenceCode1
Designing Network Design SpacesCode1
Densely Connected Convolutional NetworksCode1
Stateful ODE-Nets using Basis Function ExpansionsCode1
Compressing Features for Learning with Noisy LabelsCode1
A Second-Order Approach to Learning with Instance-Dependent Label NoiseCode1
Trainable Noise Model as an XAI evaluation method: application on Sobol for remote sensing image segmentationCode1
Training Compact CNNs for Image Classification using Dynamic-coded Filter FusionCode1
Training data-efficient image transformers & distillation through attentionCode1
Training objective drives the consistency of representational similarity across datasetsCode1
Compressive Visual RepresentationsCode1
Dense Contrastive Learning for Self-Supervised Visual Pre-TrainingCode1
Training Transformers with 4-bit IntegersCode1
Dendritic Learning-incorporated Vision Transformer for Image RecognitionCode1
DenoiseRep: Denoising Model for Representation LearningCode1
Depth Uncertainty in Neural NetworksCode1
Delving into Out-of-Distribution Detection with Medical Vision-Language ModelsCode1
Show:102550
← PrevPage 41 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