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 30013025 of 10420 papers

TitleStatusHype
Multistage Relation Network With Dual-Metric for Few-Shot Hyperspectral Image ClassificationCode1
MMViT: Multiscale Multiview Vision Transformers0
Deep Fast Vision: Accelerated Deep Transfer Learning Vision Prototyping and BeyondCode1
Tensor Decomposition for Model Reduction in Neural Networks: A Review0
From Association to Generation: Text-only Captioning by Unsupervised Cross-modal MappingCode1
Advancing Ischemic Stroke Diagnosis: A Novel Two-Stage Approach for Blood Clot Origin Identification0
ESPT: A Self-Supervised Episodic Spatial Pretext Task for Improving Few-Shot LearningCode1
PVP: Pre-trained Visual Parameter-Efficient Tuning0
iMixer: hierarchical Hopfield network implies an invertible, implicit and iterative MLP-MixerCode0
Sample-Specific Debiasing for Better Image-Text Models0
Bayesian Optimization Meets Self-DistillationCode1
Evaluating Adversarial Robustness on Document Image Classification0
Now You See Me: Robust approach to Partial Occlusions0
Function-Consistent Feature DistillationCode1
MixPro: Data Augmentation with MaskMix and Progressive Attention Labeling for Vision TransformerCode1
AwesomeMeta+: A Mixed-Prototyping Meta-Learning System Supporting AI Application Design AnywhereCode1
Graph Convolutional Networks based on Manifold Learning for Semi-Supervised Image Classification0
Improving Classification Neural Networks by using Absolute activation function (MNIST/LeNET-5 example)Code0
Vision Transformer for Efficient Chest X-ray and Gastrointestinal Image Classification0
The Case for Hierarchical Deep Learning Inference at the Network Edge0
SATIN: A Multi-Task Metadataset for Classifying Satellite Imagery using Vision-Language Models0
Learning Partial Correlation based Deep Visual Representation for Image ClassificationCode1
Exploiting Patch Sizes and Resolutions for Multi-Scale Deep Learning in Mammogram Image Classification0
WATT-EffNet: A Lightweight and Accurate Model for Classifying Aerial Disaster ImagesCode0
Graph based Label Enhancement for Multi-instance Multi-label learning0
Show:102550
← PrevPage 121 of 417Next →

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