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 201250 of 10419 papers

TitleStatusHype
ASAM: Adaptive Sharpness-Aware Minimization for Scale-Invariant Learning of Deep Neural NetworksCode2
MedFMC: A Real-world Dataset and Benchmark For Foundation Model Adaptation in Medical Image ClassificationCode2
MedMNIST v2 -- A large-scale lightweight benchmark for 2D and 3D biomedical image classificationCode2
MedViT: A Robust Vision Transformer for Generalized Medical Image ClassificationCode2
MetaFormer: A Unified Meta Framework for Fine-Grained RecognitionCode2
ECA-Net: Efficient Channel Attention for Deep Convolutional Neural NetworksCode2
Accelerating Transformers with Spectrum-Preserving Token MergingCode2
DEYO: DETR with YOLO for End-to-End Object DetectionCode2
DGR-MIL: Exploring Diverse Global Representation in Multiple Instance Learning for Whole Slide Image ClassificationCode2
Dilated Neighborhood Attention TransformerCode2
UNetFormer: A UNet-like Transformer for Efficient Semantic Segmentation of Remote Sensing Urban Scene ImageryCode2
An Overview of Deep Semi-Supervised LearningCode2
AWT: Transferring Vision-Language Models via Augmentation, Weighting, and TransportationCode2
Med-MoE: Mixture of Domain-Specific Experts for Lightweight Medical Vision-Language ModelsCode2
DenseNets Reloaded: Paradigm Shift Beyond ResNets and ViTsCode2
Deep PCB To COCO ConvertorCode2
Adapter is All You Need for Tuning Visual TasksCode2
DaViT: Dual Attention Vision TransformersCode2
AdaBelief Optimizer: Adapting Stepsizes by the Belief in Observed GradientsCode2
Neighborhood Attention TransformerCode2
Next-ViT: Next Generation Vision Transformer for Efficient Deployment in Realistic Industrial ScenariosCode2
NodeFormer: A Scalable Graph Structure Learning Transformer for Node ClassificationCode2
Decoupled Knowledge DistillationCode2
A Self-Supervised Descriptor for Image Copy DetectionCode2
AdaFisher: Adaptive Second Order Optimization via Fisher InformationCode2
Optimal Weighted Convolution for Classification and DenosingCode2
DAT++: Spatially Dynamic Vision Transformer with Deformable AttentionCode2
Class-Incremental Learning: A SurveyCode2
BatchFormerV2: Exploring Sample Relationships for Dense Representation LearningCode2
Current Trends in Deep Learning for Earth Observation: An Open-source Benchmark Arena for Image ClassificationCode2
PMC-CLIP: Contrastive Language-Image Pre-training using Biomedical DocumentsCode2
Practical Continual Forgetting for Pre-trained Vision ModelsCode2
ProxylessNAS: Direct Neural Architecture Search on Target Task and HardwareCode2
Pruning Filters for Efficient ConvNetsCode2
CrypTen: Secure Multi-Party Computation Meets Machine LearningCode2
Random Erasing Data AugmentationCode2
CrossFormer++: A Versatile Vision Transformer Hinging on Cross-scale AttentionCode2
RepVGG: Making VGG-style ConvNets Great AgainCode2
MobileOne: An Improved One millisecond Mobile BackboneCode2
RoPAWS: Robust Semi-supervised Representation Learning from Uncurated DataCode2
Cross the Gap: Exposing the Intra-modal Misalignment in CLIP via Modality InversionCode2
ALBench: A Framework for Evaluating Active Learning in Object DetectionCode2
Beyond Self-attention: External Attention using Two Linear Layers for Visual TasksCode2
Beyond Image Super-Resolution for Image Recognition with Task-Driven Perceptual LossCode2
DAMamba: Vision State Space Model with Dynamic Adaptive ScanCode2
Aligning Domain-specific Distribution and Classifier for Cross-domain Classification from Multiple SourcesCode2
Contrastive Learning Rivals Masked Image Modeling in Fine-tuning via Feature DistillationCode2
Contrastive learning of Class-agnostic Activation Map for Weakly Supervised Object Localization and Semantic SegmentationCode2
ConvMAE: Masked Convolution Meets Masked AutoencodersCode2
Context Encoding for Semantic SegmentationCode2
Show:102550
← PrevPage 5 of 209Next →

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