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 11261150 of 10420 papers

TitleStatusHype
PolyLoss: A Polynomial Expansion Perspective of Classification Loss FunctionsCode1
Surpassing the Human Accuracy: Detecting Gallbladder Cancer from USG Images with Curriculum LearningCode1
Self-supervised Learning for Sonar Image ClassificationCode1
Continual Hippocampus Segmentation with TransformersCode1
Learning with SignaturesCode1
Towards Lightweight Transformer via Group-wise Transformation for Vision-and-Language TasksCode1
Pushing the Limits of Simple Pipelines for Few-Shot Learning: External Data and Fine-Tuning Make a DifferenceCode1
DeiT III: Revenge of the ViTCode1
ViTOL: Vision Transformer for Weakly Supervised Object LocalizationCode1
ReCLIP: A Strong Zero-Shot Baseline for Referring Expression ComprehensionCode1
No Token Left Behind: Explainability-Aided Image Classification and GenerationCode1
SuperpixelGridCut, SuperpixelGridMean and SuperpixelGridMix Data AugmentationCode1
Generative Adversarial Networks for Image Augmentation in Agriculture: A Systematic ReviewCode1
Total Variation Optimization Layers for Computer VisionCode1
Fine-Grained Predicates Learning for Scene Graph GenerationCode1
Universal Representations: A Unified Look at Multiple Task and Domain LearningCode1
MetaAudio: A Few-Shot Audio Classification BenchmarkCode1
Real-time Hyperspectral Imaging in Hardware via Trained Metasurface EncodersCode1
Improving Vision Transformers by Revisiting High-frequency ComponentsCode1
Efficient Convolutional Neural Networks on Raspberry Pi for Image ClassificationCode1
Deep Hyperspectral Unmixing using Transformer NetworkCode1
Multimodal Fusion Transformer for Remote Sensing Image ClassificationCode1
Collaborative Transformers for Grounded Situation RecognitionCode1
A fuzzy distance-based ensemble of deep models for cervical cancer detectionCode1
Fair Contrastive Learning for Facial Attribute ClassificationCode1
Show:102550
← PrevPage 46 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
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