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 82768300 of 10420 papers

TitleStatusHype
Long-tailed Medical Diagnosis with Relation-aware Representation Learning and Iterative Classifier CalibrationCode0
CP-decomposition with Tensor Power Method for Convolutional Neural Networks CompressionCode0
Tensor decomposition to Compress Convolutional Layers in Deep LearningCode0
COVID-19 Detection on Chest X-Ray Images: A comparison of CNN architectures and ensemblesCode0
Frequency-Guided Masking for Enhanced Vision Self-Supervised LearningCode0
A Design Methodology for Efficient Implementation of Deconvolutional Neural Networks on an FPGACode0
Looking back at Labels: A Class based Domain Adaptation TechniqueCode0
Frequency-Temporal Attention Network for Remote Sensing Imagery Change DetectionCode0
FrequentNet: A Novel Interpretable Deep Learning Model for Image ClassificationCode0
FrImCla: A Framework for Image Classification Using Traditional and Transfer Learning TechniquesCode0
A Deep Neuro-Fuzzy Network for Image ClassificationCode0
Explaining NonLinear Classification Decisions with Deep Taylor DecompositionCode0
On Model Compression for Neural Networks: Framework, Algorithm, and Convergence GuaranteeCode0
Look-ups are not (yet) all you need for deep learning inferenceCode0
Incompatibility Clustering as a Defense Against Backdoor Poisoning AttacksCode0
Safeguarded Dynamic Label Regression for Generalized Noisy SupervisionCode0
Covariance-free Partial Least Squares: An Incremental Dimensionality Reduction MethodCode0
Explaining Neural Networks by Decoding Layer ActivationsCode0
Revisiting lp-constrained Softmax Loss: A Comprehensive StudyCode0
Losses over Labels: Weakly Supervised Learning via Direct Loss ConstructionCode0
Safeguarding Data in Multimodal AI: A Differentially Private Approach to CLIP TrainingCode0
Loss re-scaling VQA: Revisiting the LanguagePrior Problem from a Class-imbalance ViewCode0
Loss-Sensitive Generative Adversarial Networks on Lipschitz DensitiesCode0
Observer Dependent Lossy Image CompressionCode0
On the Stability of a non-hyperbolic nonlinear map with non-bounded set of non-isolated fixed points with applications to Machine LearningCode0
Show:102550
← PrevPage 332 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