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 42014225 of 10420 papers

TitleStatusHype
Hyperparameter Ensembles for Robustness and Uncertainty QuantificationCode0
HyperDID: Hyperspectral Intrinsic Image Decomposition with Deep Feature EmbeddingCode0
Hyper-Process Model: A Zero-Shot Learning algorithm for Regression Problems based on Shape AnalysisCode0
Hyperspectral image classification via a random patches networkCode0
ConvNeXt Based Neural Network for Audio Anti-SpoofingCode0
HyperbolicLR: Epoch insensitive learning rate schedulerCode0
ConViT: Improving Vision Transformers with Soft Convolutional Inductive BiasesCode0
Conviformers: Convolutionally guided Vision TransformerCode0
Network Fission Ensembles for Low-Cost Self-EnsemblesCode0
Hyperbolic Sliced-Wasserstein via Geodesic and Horospherical ProjectionsCode0
Human-in-the-Loop Visual Re-ID for Population Size EstimationCode0
Hybrid Macro/Micro Level Backpropagation for Training Deep Spiking Neural NetworksCode0
Human-imperceptible, Machine-recognizable ImagesCode0
Drop Clause: Enhancing Performance, Interpretability and Robustness of the Tsetlin MachineCode0
HybridSN: Exploring 3D-2D CNN Feature Hierarchy for Hyperspectral Image ClassificationCode0
Aggregating Deep Convolutional Features for Image RetrievalCode0
Controlling Participation in Federated Learning with FeedbackCode0
HSI-CNN: A Novel Convolution Neural Network for Hyperspectral ImageCode0
Human Activity Recognition Based on Wearable Sensor Data: A Standardization of the State-of-the-ArtCode0
HyenaPixel: Global Image Context with ConvolutionsCode0
iCAR: Bridging Image Classification and Image-text Alignment for Visual RecognitionCode0
How transfer learning is used in generative models for image classification: improved accuracyCode0
How to Use Dropout Correctly on Residual Networks with Batch NormalizationCode0
VidModEx: Interpretable and Efficient Black Box Model Extraction for High-Dimensional SpacesCode0
How Do Training Methods Influence the Utilization of Vision Models?Code0
Show:102550
← PrevPage 169 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