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 12511300 of 10419 papers

TitleStatusHype
DynaMixer: A Vision MLP Architecture with Dynamic MixingCode1
Early-Learning Regularization Prevents Memorization of Noisy LabelsCode1
Automated Learning Rate Scheduler for Large-batch TrainingCode1
Federated Adaptive Prompt Tuning for Multi-Domain Collaborative LearningCode1
Cross-Domain Ensemble Distillation for Domain GeneralizationCode1
CrossFormer: A Versatile Vision Transformer Hinging on Cross-scale AttentionCode1
EEEA-Net: An Early Exit Evolutionary Neural Architecture SearchCode1
CoV-TI-Net: Transferred Initialization with Modified End Layer for COVID-19 DiagnosisCode1
A Bregman Learning Framework for Sparse Neural NetworksCode1
Automatically designing CNN architectures using genetic algorithm for image classificationCode1
Efficient Classification of Very Large Images with Tiny ObjectsCode1
Benchmarking and scaling of deep learning models for land cover image classificationCode1
CPrune: Compiler-Informed Model Pruning for Efficient Target-Aware DNN ExecutionCode1
BAGAN: Data Augmentation with Balancing GANCode1
Aggregated Residual Transformations for Deep Neural NetworksCode1
COVID-CXNet: Detecting COVID-19 in Frontal Chest X-ray Images using Deep LearningCode1
CrAM: A Compression-Aware MinimizerCode1
CosPGD: an efficient white-box adversarial attack for pixel-wise prediction tasksCode1
All you need is a good initCode1
A survey on attention mechanisms for medical applications: are we moving towards better algorithms?Code1
Almost-Orthogonal Layers for Efficient General-Purpose Lipschitz NetworksCode1
Beyond Class-Conditional Assumption: A Primary Attempt to Combat Instance-Dependent Label NoiseCode1
Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy LabelsCode1
CoProNN: Concept-based Prototypical Nearest Neighbors for Explaining Vision ModelsCode1
Automatic Recognition of Abdominal Organs in Ultrasound Images based on Deep Neural Networks and K-Nearest-Neighbor ClassificationCode1
Beyond Categorical Label Representations for Image ClassificationCode1
Convolution-enhanced Evolving Attention NetworksCode1
ELSA: Enhanced Local Self-Attention for Vision TransformerCode1
CorGAN: Correlation-Capturing Convolutional Generative Adversarial Networks for Generating Synthetic Healthcare RecordsCode1
Co-Tuning for Transfer LearningCode1
AutoMix: Unveiling the Power of Mixup for Stronger ClassifiersCode1
BiTr-Unet: a CNN-Transformer Combined Network for MRI Brain Tumor SegmentationCode1
Enhanced OoD Detection through Cross-Modal Alignment of Multi-Modal RepresentationsCode1
Enhance Image Classification via Inter-Class Image Mixup with Diffusion ModelCode1
AlphaNet: Improved Training of Supernets with Alpha-DivergenceCode1
Enhancing Few-Shot Image Classification through Learnable Multi-Scale Embedding and Attention MechanismsCode1
AutoSpeech: Neural Architecture Search for Speaker RecognitionCode1
Convolutional Sequence to Sequence LearningCode1
Convolutional Channel-wise Competitive Learning for the Forward-Forward AlgorithmCode1
Entroformer: A Transformer-based Entropy Model for Learned Image CompressionCode1
AutoVP: An Automated Visual Prompting Framework and BenchmarkCode1
EPSANet: An Efficient Pyramid Squeeze Attention Block on Convolutional Neural NetworkCode1
Convolutional Spiking Neural Networks for Spatio-Temporal Feature ExtractionCode1
Error-Bounded Correction of Noisy LabelsCode1
Systematic comparison of semi-supervised and self-supervised learning for medical image classificationCode1
Evaluating histopathology transfer learning with ChampKitCode1
Evaluating the Adversarial Robustness of Adaptive Test-time DefensesCode1
Evaluating the visualization of what a Deep Neural Network has learnedCode1
EViT: An Eagle Vision Transformer with Bi-Fovea Self-AttentionCode1
No Routing Needed Between CapsulesCode1
Show:102550
← PrevPage 26 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