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 36513675 of 10420 papers

TitleStatusHype
Deep Active Learning with Augmentation-based Consistency EstimationCode0
Reducing Texture Bias of Deep Neural Networks via Edge Enhancing DiffusionCode0
ImageNet Classification with Deep Convolutional Neural NetworksCode0
Err on the Side of Texture: Texture Bias on Real DataCode0
ImageNot: A contrast with ImageNet preserves model rankingsCode0
Adaptive Cascading Network for Continual Test-Time AdaptationCode0
All You Need is a Few Shifts: Designing Efficient Convolutional Neural Networks for Image ClassificationCode0
DED: Diagnostic Evidence Distillation for acne severity grading on face imagesCode0
Image Quality Assessment Guided Deep Neural Networks TrainingCode0
Image Classification with Hierarchical Multigraph NetworksCode0
Automatic Data Augmentation via Invariance-Constrained LearningCode0
Automatic Configuration of Deep Neural Networks with EGOCode0
Application of a Convolutional Neural Network for image classification to the analysis of collisions in High Energy PhysicsCode0
Unsupervised Attention Mechanism across Neural Network LayersCode0
Decoupled Greedy Learning of CNNsCode0
Regularization of Neural Networks using DropConnectCode0
Image Classification with Classic and Deep Learning TechniquesCode0
Image Classification Using Singular Value Decomposition and OptimizationCode0
ETran: Energy-Based Transferability EstimationCode0
EurNet: Efficient Multi-Range Relational Modeling of Spatial Multi-Relational DataCode0
Image Classification with CondenseNeXt for ARM-Based Computing PlatformsCode0
Image-Caption Encoding for Improving Zero-Shot GeneralizationCode0
EVA: Exploring the Limits of Masked Visual Representation Learning at ScaleCode0
Decompose-and-Compose: A Compositional Approach to Mitigating Spurious CorrelationCode0
Image classification and retrieval with random depthwise signed convolutional neural networksCode0
Show:102550
← PrevPage 147 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