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 20012025 of 10420 papers

TitleStatusHype
UniformAugment: A Search-free Probabilistic Data Augmentation ApproachCode1
Regularizing Class-wise Predictions via Self-knowledge DistillationCode1
MUXConv: Information Multiplexing in Convolutional Neural NetworksCode1
TResNet: High Performance GPU-Dedicated ArchitectureCode1
An Open-source Tool for Hyperspectral Image Augmentation in TensorflowCode1
DHP: Differentiable Meta Pruning via HyperNetworksCode1
Rethinking Depthwise Separable Convolutions: How Intra-Kernel Correlations Lead to Improved MobileNetsCode1
Designing Network Design SpacesCode1
Convolutional Spiking Neural Networks for Spatio-Temporal Feature ExtractionCode1
GAN-based Priors for Quantifying UncertaintyCode1
Hit-Detector: Hierarchical Trinity Architecture Search for Object DetectionCode1
Circumventing Outliers of AutoAugment with Knowledge DistillationCode1
Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need?Code1
Meta Pseudo LabelsCode1
Adversarial Continual LearningCode1
Adversarial Robustness on In- and Out-Distribution Improves ExplainabilityCode1
Overinterpretation reveals image classification model pathologiesCode1
On Translation Invariance in CNNs: Convolutional Layers can Exploit Absolute Spatial LocationCode1
Synthesizing human-like sketches from natural images using a conditional convolutional decoderCode1
DeepEMD: Differentiable Earth Mover's Distance for Few-Shot LearningCode1
SOS: Selective Objective Switch for Rapid Immunofluorescence Whole Slide Image ClassificationCode1
Improved Baselines with Momentum Contrastive LearningCode1
Π-nets: Deep Polynomial Neural NetworksCode1
Clean-Label Backdoor Attacks on Video Recognition ModelsCode1
TaskNorm: Rethinking Batch Normalization for Meta-LearningCode1
Show:102550
← PrevPage 81 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