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 85018525 of 10420 papers

TitleStatusHype
Enhancing Fine-Grained Visual Recognition in the Low-Data Regime Through Feature Magnitude RegularizationCode0
Acne Severity Grading on Face Images via Extraction and Guidance of Prior KnowledgeCode0
MASS: MoErging through Adaptive Subspace SelectionCode0
Enhancing Cross-task Black-Box Transferability of Adversarial Examples with Dispersion ReductionCode0
Automated wildlife image classification: An active learning tool for ecological applicationsCode0
Enhancing Cross-Prompt Transferability in Vision-Language Models through Contextual Injection of Target TokensCode0
Classification Utility, Fairness, and Compactness via Tunable Information Bottleneck and Rényi MeasuresCode0
Continual Learning with Strong Experience ReplayCode0
Automated Seed Quality Testing System using GAN & Active LearningCode0
Matrix capsules with EM routingCode0
GLoMo: Unsupervisedly Learned Relational Graphs as Transferable RepresentationsCode0
GLUSE: Enhanced Channel-Wise Adaptive Gated Linear Units SE for Onboard Satellite Earth Observation Image ClassificationCode0
Glyce: Glyph-vectors for Chinese Character RepresentationsCode0
Automated Search for Configurations of Deep Neural Network ArchitecturesCode0
Redundant representations help generalization in wide neural networksCode0
Continual Learning with Deep Streaming Regularized Discriminant AnalysisCode0
Continual Learning with Deep Generative ReplayCode0
PUNCH: Positive UNlabelled Classification based information retrieval in Hyperspectral imagesCode0
Analysis of Confident-Classifiers for Out-of-distribution DetectionCode0
Automated Knowledge Distillation via Monte Carlo Tree SearchCode0
OpenAL: An Efficient Deep Active Learning Framework for Open-Set Pathology Image ClassificationCode0
Enhancing Adaptive Deep Networks for Image Classification via Uncertainty-aware Decision FusionCode0
Maximally Invariant Data Perturbation as ExplanationCode0
Going Deeper with Contextual CNN for Hyperspectral Image ClassificationCode0
Enhance the Visual Representation via Discrete Adversarial TrainingCode0
Show:102550
← PrevPage 341 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