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 10420 papers

TitleStatusHype
Medical Image Classification with KAN-Integrated Transformers and Dilated Neighborhood AttentionCode2
ECA-Net: Efficient Channel Attention for Deep Convolutional Neural NetworksCode2
EdgeNeXt: Efficiently Amalgamated CNN-Transformer Architecture for Mobile Vision ApplicationsCode2
UNetFormer: A UNet-like Transformer for Efficient Semantic Segmentation of Remote Sensing Urban Scene ImageryCode2
Accelerating Transformers with Spectrum-Preserving Token MergingCode2
MetaFormer Is Actually What You Need for VisionCode2
Dilated Neighborhood Attention TransformerCode2
A Self-Supervised Descriptor for Image Copy DetectionCode2
DGR-MIL: Exploring Diverse Global Representation in Multiple Instance Learning for Whole Slide Image ClassificationCode2
MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision TransformerCode2
Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference timeCode2
Med-MoE: Mixture of Domain-Specific Experts for Lightweight Medical Vision-Language ModelsCode2
DenseNets Reloaded: Paradigm Shift Beyond ResNets and ViTsCode2
Axial-DeepLab: Stand-Alone Axial-Attention for Panoptic SegmentationCode2
An Overview of Deep Semi-Supervised LearningCode2
Adapter is All You Need for Tuning Visual TasksCode2
AdaBelief Optimizer: Adapting Stepsizes by the Belief in Observed GradientsCode2
Multi-Representation Adaptation Network for Cross-domain Image ClassificationCode2
AdaFisher: Adaptive Second Order Optimization via Fisher InformationCode2
Next-ViT: Next Generation Vision Transformer for Efficient Deployment in Realistic Industrial ScenariosCode2
Deep PCB To COCO ConvertorCode2
No More Strided Convolutions or Pooling: A New CNN Building Block for Low-Resolution Images and Small ObjectsCode2
BatchFormerV2: Exploring Sample Relationships for Dense Representation LearningCode2
Decoupled Knowledge DistillationCode2
Agent Attention: On the Integration of Softmax and Linear AttentionCode2
DaViT: Dual Attention Vision TransformersCode2
Class-Incremental Learning: A SurveyCode2
DEYO: DETR with YOLO for End-to-End Object DetectionCode2
PathGen-1.6M: 1.6 Million Pathology Image-text Pairs Generation through Multi-agent CollaborationCode2
MogaNet: Multi-order Gated Aggregation NetworkCode2
Prompt Pre-Training with Twenty-Thousand Classes for Open-Vocabulary Visual RecognitionCode2
ProxylessNAS: Direct Neural Architecture Search on Target Task and HardwareCode2
ALBench: A Framework for Evaluating Active Learning in Object DetectionCode2
QDrop: Randomly Dropping Quantization for Extremely Low-bit Post-Training QuantizationCode2
MobileOne: An Improved One millisecond Mobile BackboneCode2
DAMamba: Vision State Space Model with Dynamic Adaptive ScanCode2
CrypTen: Secure Multi-Party Computation Meets Machine LearningCode2
RepVGG: Making VGG-style ConvNets Great AgainCode2
Cross the Gap: Exposing the Intra-modal Misalignment in CLIP via Modality InversionCode2
Current Trends in Deep Learning for Earth Observation: An Open-source Benchmark Arena for Image ClassificationCode2
DataDream: Few-shot Guided Dataset GenerationCode2
S^2Mamba: A Spatial-spectral State Space Model for Hyperspectral Image ClassificationCode2
Beyond Self-attention: External Attention using Two Linear Layers for Visual TasksCode2
Beyond Image Super-Resolution for Image Recognition with Task-Driven Perceptual LossCode2
ConvMAE: Masked Convolution Meets Masked AutoencodersCode2
Scaling Up Visual and Vision-Language Representation Learning With Noisy Text SupervisionCode2
Contrastive Learning Rivals Masked Image Modeling in Fine-tuning via Feature DistillationCode2
CroCo: Self-Supervised Pre-training for 3D Vision Tasks by Cross-View CompletionCode2
Shifts 2.0: Extending The Dataset of Real Distributional ShiftsCode2
Continual Forgetting for Pre-trained Vision ModelsCode2
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
5DaViT-HTop 1 Accuracy90.2Unverified
6Meta Pseudo Labels (EfficientNet-L2)Top 1 Accuracy90.2Unverified
7SwinV2-GTop 1 Accuracy90.17Unverified
8MAWS (ViT-6.5B)Top 1 Accuracy90.1Unverified
9Florence-CoSwin-HTop 1 Accuracy90.05Unverified
10Meta Pseudo Labels (EfficientNet-B6-Wide)Top 1 Accuracy90Unverified