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 201225 of 10419 papers

TitleStatusHype
DenseNets Reloaded: Paradigm Shift Beyond ResNets and ViTsCode2
Advancing Spiking Neural Networks for Sequential Modeling with Central Pattern GeneratorsCode2
AdaBelief Optimizer: Adapting Stepsizes by the Belief in Observed GradientsCode2
ECA-Net: Efficient Channel Attention for Deep Convolutional Neural NetworksCode2
AutoFormer: Searching Transformers for Visual RecognitionCode2
MedFMC: A Real-world Dataset and Benchmark For Foundation Model Adaptation in Medical Image ClassificationCode2
MobileOne: An Improved One millisecond Mobile BackboneCode2
Class-Incremental Learning: A SurveyCode2
Deep PCB To COCO ConvertorCode2
MIC: Masked Image Consistency for Context-Enhanced Domain AdaptationCode2
DaViT: Dual Attention Vision TransformersCode2
Mitigate the Gap: Investigating Approaches for Improving Cross-Modal Alignment in CLIPCode2
DAT++: Spatially Dynamic Vision Transformer with Deformable AttentionCode2
Decoupled Knowledge DistillationCode2
DAMamba: Vision State Space Model with Dynamic Adaptive ScanCode2
DataDream: Few-shot Guided Dataset GenerationCode2
CrypTen: Secure Multi-Party Computation Meets Machine LearningCode2
Momentum Centering and Asynchronous Update for Adaptive Gradient MethodsCode2
Current Trends in Deep Learning for Earth Observation: An Open-source Benchmark Arena for Image ClassificationCode2
ParC-Net: Position Aware Circular Convolution with Merits from ConvNets and TransformerCode2
Contrastive Learning Rivals Masked Image Modeling in Fine-tuning via Feature DistillationCode2
MultiMAE: Multi-modal Multi-task Masked AutoencodersCode2
ConvMAE: Masked Convolution Meets Masked AutoencodersCode2
Continual Forgetting for Pre-trained Vision ModelsCode2
Context Encoding for Semantic SegmentationCode2
Show:102550
← PrevPage 9 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