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 15511575 of 10420 papers

TitleStatusHype
CellMix: A General Instance Relationship based Method for Data Augmentation Towards Pathology Image ClassificationCode1
Feature Extraction for Hyperspectral Imagery: The Evolution from Shallow to Deep (Overview and Toolbox)Code1
Feature Guided Masked Autoencoder for Self-supervised Learning in Remote SensingCode1
Bootstrap your own latent: A new approach to self-supervised LearningCode1
FedBABU: Towards Enhanced Representation for Federated Image ClassificationCode1
BossNAS: Exploring Hybrid CNN-transformers with Block-wisely Self-supervised Neural Architecture SearchCode1
BottleFit: Learning Compressed Representations in Deep Neural Networks for Effective and Efficient Split ComputingCode1
Federated Model Aggregation via Self-Supervised Priors for Highly Imbalanced Medical Image ClassificationCode1
Robust Models Are More Interpretable Because Attributions Look NormalCode1
DiagSet: a dataset for prostate cancer histopathological image classificationCode1
DIANet: Dense-and-Implicit Attention NetworkCode1
MoBYv2AL: Self-supervised Active Learning for Image ClassificationCode1
Bounding Boxes Are All We Need: Street View Image Classification via Context Encoding of Detected BuildingsCode1
An Ensemble of Simple Convolutional Neural Network Models for MNIST Digit RecognitionCode1
Differentiable Model Compression via Pseudo Quantization NoiseCode1
Differentiable Model Scaling using Differentiable TopkCode1
CDUL: CLIP-Driven Unsupervised Learning for Multi-Label Image ClassificationCode1
FCCNs: Fully Complex-valued Convolutional Networks using Complex-valued Color Model and Loss FunctionCode1
DiffMIC: Dual-Guidance Diffusion Network for Medical Image ClassificationCode1
MOFI: Learning Image Representations from Noisy Entity Annotated ImagesCode1
A Neural Dirichlet Process Mixture Model for Task-Free Continual LearningCode1
Diffusion Mechanism in Residual Neural Network: Theory and ApplicationsCode1
FC-KAN: Function Combinations in Kolmogorov-Arnold NetworksCode1
FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture SearchCode1
CEFHRI: A Communication Efficient Federated Learning Framework for Recognizing Industrial Human-Robot InteractionCode1
Show:102550
← PrevPage 63 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