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 75767600 of 10420 papers

TitleStatusHype
Neural Architecture Search for Lightweight Non-Local NetworksCode1
Group Based Deep Shared Feature Learning for Fine-grained Image Classification0
ObjectNet Dataset: Reanalysis and CorrectionCode1
Generative Adversarial Networks Based on Collaborative Learning and Attention Mechanism for Hyperspectral Image Classification0
Gradient Centralization: A New Optimization Technique for Deep Neural NetworksCode1
Hierarchical Image Classification using Entailment Cone EmbeddingsCode1
Predicting the outputs of finite deep neural networks trained with noisy gradients0
Learning Sparse & Ternary Neural Networks with Entropy-Constrained Trained Ternarization (EC2T)Code0
Learning Representations For Images With Hierarchical LabelsCode1
In Automation We Trust: Investigating the Role of Uncertainty in Active Learning Systems0
Controllable Orthogonalization in Training DNNsCode1
Adversarial Learning for Personalized Tag RecommendationCode0
Editable Neural NetworksCode1
Improving Deep Hyperspectral Image Classification Performance with Spectral Unmixing0
Binary Neural Networks: A SurveyCode2
UniformAugment: A Search-free Probabilistic Data Augmentation ApproachCode1
Regularizing Class-wise Predictions via Self-knowledge DistillationCode1
MUXConv: Information Multiplexing in Convolutional Neural NetworksCode1
Generative Latent Implicit Conditional Optimization when Learning from Small SampleCode1
Incremental Learning In Online Scenario0
An Open-source Tool for Hyperspectral Image Augmentation in TensorflowCode1
Rethinking Depthwise Separable Convolutions: How Intra-Kernel Correlations Lead to Improved MobileNetsCode1
DHP: Differentiable Meta Pruning via HyperNetworksCode1
Designing Network Design SpacesCode1
Improved Gradient based Adversarial Attacks for Quantized NetworksCode0
Show:102550
← PrevPage 304 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