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 151175 of 10419 papers

TitleStatusHype
ERS: a novel comprehensive endoscopy image dataset for machine learning, compliant with the MST 3.0 specificationCode2
EfficientViM: Efficient Vision Mamba with Hidden State Mixer based State Space DualityCode2
Aligning Domain-specific Distribution and Classifier for Cross-domain Classification from Multiple SourcesCode2
Fixing the train-test resolution discrepancyCode2
MogaNet: Multi-order Gated Aggregation NetworkCode2
ALBench: A Framework for Evaluating Active Learning in Object DetectionCode2
Efficient Multi-Scale Attention Module with Cross-Spatial LearningCode2
Agent Attention: On the Integration of Softmax and Linear AttentionCode2
ECA-Net: Efficient Channel Attention for Deep Convolutional Neural NetworksCode2
ParC-Net: Position Aware Circular Convolution with Merits from ConvNets and TransformerCode2
Dilated Neighborhood Attention TransformerCode2
EdgeNeXt: Efficiently Amalgamated CNN-Transformer Architecture for Mobile Vision ApplicationsCode2
Fixing the train-test resolution discrepancy: FixEfficientNetCode2
Effective Data Augmentation With Diffusion ModelsCode2
UNetFormer: A UNet-like Transformer for Efficient Semantic Segmentation of Remote Sensing Urban Scene ImageryCode2
GPipe: Efficient Training of Giant Neural Networks using Pipeline ParallelismCode2
DenseNets Reloaded: Paradigm Shift Beyond ResNets and ViTsCode2
Deep PCB To COCO ConvertorCode2
DaViT: Dual Attention Vision TransformersCode2
Accelerating Transformers with Spectrum-Preserving Token MergingCode2
Decoupled Knowledge DistillationCode2
DataDream: Few-shot Guided Dataset GenerationCode2
DAT++: Spatially Dynamic Vision Transformer with Deformable AttentionCode2
FasterViT: Fast Vision Transformers with Hierarchical AttentionCode2
Class-Incremental Learning: A SurveyCode2
Show:102550
← PrevPage 7 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