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 276300 of 10419 papers

TitleStatusHype
Beyond Self-attention: External Attention using Two Linear Layers for Visual TasksCode2
Swin Transformer: Hierarchical Vision Transformer using Shifted WindowsCode2
Involution: Inverting the Inherence of Convolution for Visual RecognitionCode2
Learning Transferable Visual Models From Natural Language SupervisionCode2
ASAM: Adaptive Sharpness-Aware Minimization for Scale-Invariant Learning of Deep Neural NetworksCode2
LambdaNetworks: Modeling Long-Range Interactions Without AttentionCode2
Scaling Up Visual and Vision-Language Representation Learning With Noisy Text SupervisionCode2
Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNetCode2
Bottleneck Transformers for Visual RecognitionCode2
Simplifying Object Segmentation with PixelLib LibraryCode2
RepVGG: Making VGG-style ConvNets Great AgainCode2
AdaBelief Optimizer: Adapting Stepsizes by the Belief in Observed GradientsCode2
Sharpness-Aware Minimization for Efficiently Improving GeneralizationCode2
Generative Pretraining from PixelsCode2
Unsupervised Learning of Visual Features by Contrasting Cluster AssignmentsCode2
An Overview of Deep Semi-Supervised LearningCode2
SCAN: Learning to Classify Images without LabelsCode2
Supervised Contrastive LearningCode2
ktrain: A Low-Code Library for Augmented Machine LearningCode2
X3D: Expanding Architectures for Efficient Video RecognitionCode2
Binary Neural Networks: A SurveyCode2
Fixing the train-test resolution discrepancy: FixEfficientNetCode2
Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic SegmentationCode2
A Simple Framework for Contrastive Learning of Visual RepresentationsCode2
FixMatch: Simplifying Semi-Supervised Learning with Consistency and ConfidenceCode2
Show:102550
← PrevPage 12 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