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 151200 of 10419 papers

TitleStatusHype
Parameter-Efficient Fine-Tuning with Discrete Fourier TransformCode2
MMEarth: Exploring Multi-Modal Pretext Tasks For Geospatial Representation LearningCode2
S^2Mamba: A Spatial-spectral State Space Model for Hyperspectral Image ClassificationCode2
An Experimental Study on Exploring Strong Lightweight Vision Transformers via Masked Image Modeling Pre-TrainingCode2
Med-MoE: Mixture of Domain-Specific Experts for Lightweight Medical Vision-Language ModelsCode2
HGRN2: Gated Linear RNNs with State ExpansionCode2
Beyond Image Super-Resolution for Image Recognition with Task-Driven Perceptual LossCode2
DenseNets Reloaded: Paradigm Shift Beyond ResNets and ViTsCode2
Continual Forgetting for Pre-trained Vision ModelsCode2
Trainable Fractional Fourier TransformCode2
SURE: SUrvey REcipes for building reliable and robust deep networksCode2
DEYO: DETR with YOLO for End-to-End Object DetectionCode2
SHViT: Single-Head Vision Transformer with Memory Efficient Macro DesignCode2
Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space ModelCode2
UV-SAM: Adapting Segment Anything Model for Urban Village IdentificationCode2
Learn From Zoom: Decoupled Supervised Contrastive Learning For WCE Image ClassificationCode2
Learning Vision from Models Rivals Learning Vision from DataCode2
State-of-the-Art in Nudity Classification: A Comparative AnalysisCode2
Agent Attention: On the Integration of Softmax and Linear AttentionCode2
TrackDiffusion: Tracklet-Conditioned Video Generation via Diffusion ModelsCode2
TransNeXt: Robust Foveal Visual Perception for Vision TransformersCode2
Adapter is All You Need for Tuning Visual TasksCode2
TransXNet: Learning Both Global and Local Dynamics with a Dual Dynamic Token Mixer for Visual RecognitionCode2
Monarch Mixer: A Simple Sub-Quadratic GEMM-Based ArchitectureCode2
CLIPSelf: Vision Transformer Distills Itself for Open-Vocabulary Dense PredictionCode2
DAT++: Spatially Dynamic Vision Transformer with Deformable AttentionCode2
RevColV2: Exploring Disentangled Representations in Masked Image ModelingCode2
RemoteCLIP: A Vision Language Foundation Model for Remote SensingCode2
MedFMC: A Real-world Dataset and Benchmark For Foundation Model Adaptation in Medical Image ClassificationCode2
NodeFormer: A Scalable Graph Structure Learning Transformer for Node ClassificationCode2
FasterViT: Fast Vision Transformers with Hierarchical AttentionCode2
Efficient Multi-Scale Attention Module with Cross-Spatial LearningCode2
Unicom: Universal and Compact Representation Learning for Image RetrievalCode2
Prompt Pre-Training with Twenty-Thousand Classes for Open-Vocabulary Visual RecognitionCode2
Your Diffusion Model is Secretly a Zero-Shot ClassifierCode2
BiFormer: Vision Transformer with Bi-Level Routing AttentionCode2
PMC-CLIP: Contrastive Language-Image Pre-training using Biomedical DocumentsCode2
CrossFormer++: A Versatile Vision Transformer Hinging on Cross-scale AttentionCode2
Stabilizing Transformer Training by Preventing Attention Entropy CollapseCode2
RoPAWS: Robust Semi-supervised Representation Learning from Uncurated DataCode2
MedViT: A Robust Vision Transformer for Generalized Medical Image ClassificationCode2
Stitchable Neural NetworksCode2
Simple Hardware-Efficient Long Convolutions for Sequence ModelingCode2
Understanding Why ViT Trains Badly on Small Datasets: An Intuitive PerspectiveCode2
Effective Data Augmentation With Diffusion ModelsCode2
Class-Incremental Learning: A SurveyCode2
SeaFormer++: Squeeze-enhanced Axial Transformer for Mobile Visual RecognitionCode2
Reversible Column NetworksCode2
MIC: Masked Image Consistency for Context-Enhanced Domain AdaptationCode2
CLIP-ReID: Exploiting Vision-Language Model for Image Re-Identification without Concrete Text LabelsCode2
Show:102550
← PrevPage 4 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