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 92019225 of 10420 papers

TitleStatusHype
DiffFormer: a Differential Spatial-Spectral Transformer for Hyperspectral Image ClassificationCode0
DiffExplainer: Unveiling Black Box Models Via Counterfactual GenerationCode0
Performance of Gaussian Mixture Model Classifiers on Embedded Feature SpacesCode0
Differential Privacy Has Disparate Impact on Model AccuracyCode0
Improvising the Learning of Neural Networks on Hyperspherical ManifoldCode0
Multi-Label Feature Selection Using Adaptive and Transformed RelevanceCode0
All Grains, One Scheme (AGOS): Learning Multi-grain Instance Representation for Aerial Scene ClassificationCode0
Differentially Private Image Classification from FeaturesCode0
NOVUM: Neural Object Volumes for Robust Object ClassificationCode0
Inception-inspired LSTM for Next-frame Video PredictionCode0
DiCENet: Dimension-wise Convolutions for Efficient NetworksCode0
DiagViB-6: A Diagnostic Benchmark Suite for Vision Models in the Presence of Shortcut and Generalization OpportunitiesCode0
Diagnosing Model Performance Under Distribution ShiftCode0
Diagnosing and Mitigating Modality Interference in Multimodal Large Language ModelsCode0
Multi-Label Noise Robust Collaborative Learning for Remote Sensing Image ClassificationCode0
Rapid-INR: Storage Efficient CPU-free DNN Training Using Implicit Neural RepresentationCode0
Artificial Generation of Big Data for Improving Image Classification: A Generative Adversarial Network Approach on SAR DataCode0
A Rotation Meanout Network with Invariance for Dermoscopy Image Classification and RetrievalCode0
DGCNet: An Efficient 3D-Densenet based on Dynamic Group Convolution for Hyperspectral Remote Sensing Image ClassificationCode0
Understanding Intrinsic Robustness Using Label UncertaintyCode0
Multi-label Iterated Learning for Image Classification with Label AmbiguityCode0
Increasing-Margin Adversarial (IMA) Training to Improve Adversarial Robustness of Neural NetworksCode0
DFTS2: Simulating Deep Feature Transmission Over Packet Loss ChannelsCode0
CBIR using features derived by Deep LearningCode0
Multi-Label Logo Recognition and Retrieval based on Weighted Fusion of Neural FeaturesCode0
Show:102550
← PrevPage 369 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