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 94269450 of 10420 papers

TitleStatusHype
Deep transfer learning method based on automatic domain alignment and moment matchingCode0
Deep Sub-Ensembles for Fast Uncertainty Estimation in Image ClassificationCode0
A Consensual Collaborative Learning Method for Remote Sensing Image Classification Under Noisy Multi-LabelsCode0
Successive Embedding and Classification Loss for Aerial Image ClassificationCode0
Multi-level Relation Learning for Cross-domain Few-shot Hyperspectral Image ClassificationCode0
3D Wavelet Convolutions with Extended Receptive Fields for Hyperspectral Image ClassificationCode0
Recent Advances in Deep Learning for Object DetectionCode0
Joint Learning of Neural Networks via Iterative Reweighted Least SquaresCode0
Classification with Runge-Kutta networks and feature space augmentationCode0
3D-Convolution Guided Spectral-Spatial Transformer for Hyperspectral Image ClassificationCode0
DeepSplit: Scalable Verification of Deep Neural Networks via Operator SplittingCode0
Joint Optimization Framework for Learning with Noisy LabelsCode0
Volley Revolver: A Novel Matrix-Encoding Method for Privacy-Preserving Neural Networks (Inference)Code0
Poisson Reweighted Laplacian Uncertainty Sampling for Graph-based Active LearningCode0
MUNBa: Machine Unlearning via Nash BargainingCode0
JPEG Inspired Deep LearningCode0
Polarimetric Convolutional Network for PolSAR Image ClassificationCode0
Robust Attacks against Multiple ClassifiersCode0
Polarity is all you need to learn and transfer fasterCode0
MUST-CNN: A Multilayer Shift-and-Stitch Deep Convolutional Architecture for Sequence-based Protein Structure PredictionCode0
Exploring Robustness of Image Recognition Models on Hardware AcceleratorsCode0
Excitement Surfeited Turns to Errors: Deep Learning Testing Framework Based on Excitable NeuronsCode0
DeepSearch: A Simple and Effective Blackbox Attack for Deep Neural NetworksCode0
DeepSat V2: Feature Augmented Convolutional Neural Nets for Satellite Image ClassificationCode0
KANICE: Kolmogorov-Arnold Networks with Interactive Convolutional ElementsCode0
Show:102550
← PrevPage 378 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