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 95269550 of 10420 papers

TitleStatusHype
Deep Nets with Subsampling Layers Unwittingly Discard Useful Activations at Test-TimeCode0
Deep Multi-View Spatial-Temporal Network for Taxi Demand PredictionCode0
L3DMC: Lifelong Learning using Distillation via Mixed-Curvature SpaceCode0
Label Consistent Fisher Vectors for Supervised Feature AggregationCode0
Boosting Ensemble Accuracy by Revisiting Ensemble Diversity MetricsCode0
Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video ClassificationCode0
Recoverable Privacy-Preserving Image Classification through Noise-like Adversarial ExamplesCode0
Pose Neural Fabrics SearchCode0
Label Embedded Dictionary Learning for Image ClassificationCode0
A noisy elephant in the room: Is your out-of-distribution detector robust to label noise?Code0
Label-Embedding for Image ClassificationCode0
Boosting Domain Incremental Learning: Selecting the Optimal Parameters is All You NeedCode0
Recovering from Random Pruning: On the Plasticity of Deep Convolutional Neural NetworksCode0
NeSyFOLD: Neurosymbolic Framework for Interpretable Image ClassificationCode0
Deep Multimodality Model for Multi-task Multi-view LearningCode0
Label Ranker: Self-Aware Preference for Classification Label Position in Visual Masked Self-Supervised Pre-Trained ModelCode0
Deep Modeling and Optimization of Medical Image ClassificationCode0
Boosting Deep Ensemble Performance with Hierarchical PruningCode0
Label Smarter, Not Harder: CleverLabel for Faster Annotation of Ambiguous Image Classification with Higher QualityCode0
NetAdapt: Platform-Aware Neural Network Adaptation for Mobile ApplicationsCode0
Label Structure Preserving Contrastive Embedding for Multi-Label Learning with Missing LabelsCode0
Posterior Uncertainty Quantification in Neural Networks using Data AugmentationCode0
Boosting Adversarial Transferability across Model Genus by Deformation-Constrained WarpingCode0
BlockQNN: Efficient Block-wise Neural Network Architecture GenerationCode0
Active Generation for Image ClassificationCode0
Show:102550
← PrevPage 382 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
10Meta Pseudo Labels (EfficientNet-B6-Wide)Top 1 Accuracy90Unverified