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 85518575 of 10420 papers

TitleStatusHype
Deep Neural Networks for Marine Debris Detection in Sonar Images0
Hierarchically Structured Meta-learningCode0
Multi-Agent Image Classification via Reinforcement LearningCode0
CutMix: Regularization Strategy to Train Strong Classifiers with Localizable FeaturesCode1
A novel statistical metric learning for hyperspectral image classification0
Understanding and Utilizing Deep Neural Networks Trained with Noisy LabelsCode1
Breast cancer image classification on WSI with spatial correlationsCode0
Generative Adversarial Networks and Conditional Random Fields for Hyperspectral Image Classification0
Budgeted Training: Rethinking Deep Neural Network Training Under Resource ConstraintsCode0
Multitask Deep Learning with Spectral Knowledge for Hyperspectral Image ClassificationCode0
Breast Tumor Classification and Segmentation using Convolutional Neural Networks0
Single-Path NAS: Device-Aware Efficient ConvNet Design0
Learning Loss for Active LearningCode1
Spatial-Spectral Feature Extraction via Deep ConvLSTM Neural Networks for Hyperspectral Image Classification0
Improving Discrete Latent Representations With Differentiable Approximation Bridges0
S4L: Self-Supervised Semi-Supervised LearningCode0
Seesaw-Net: Convolution Neural Network With Uneven Group ConvolutionCode0
What Do Single-view 3D Reconstruction Networks Learn?0
Enhancing Cross-task Transferability of Adversarial Examples with Dispersion ReductionCode0
Fast-DENSER++: Evolving Fully-Trained Deep Artificial Neural Networks0
AutoAssist: A Framework to Accelerate Training of Deep Neural NetworksCode1
Advancements in Image Classification using Convolutional Neural Network0
Skin Lesion Classification Using CNNs with Patch-Based Attention and Diagnosis-Guided Loss WeightingCode0
High Frequency Residual Learning for Multi-Scale Image Classification0
Locality and Structure Regularized Low Rank Representation for Hyperspectral Image Classification0
Show:102550
← PrevPage 343 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