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 125 of 10419 papers

TitleStatusHype
Visual-RFT: Visual Reinforcement Fine-TuningCode7
Mini-Gemini: Mining the Potential of Multi-modality Vision Language ModelsCode7
MambaVision: A Hybrid Mamba-Transformer Vision BackboneCode7
MambaOut: Do We Really Need Mamba for Vision?Code7
AutoTrain: No-code training for state-of-the-art modelsCode7
Marigold: Affordable Adaptation of Diffusion-Based Image Generators for Image AnalysisCode7
MiniGPT-v2: large language model as a unified interface for vision-language multi-task learningCode7
Patch n' Pack: NaViT, a Vision Transformer for any Aspect Ratio and ResolutionCode6
DINOv2: Learning Robust Visual Features without SupervisionCode6
FlashAttention: Fast and Memory-Efficient Exact Attention with IO-AwarenessCode6
Visual Instruction TuningCode6
Improved Baselines with Visual Instruction TuningCode6
Efficient Multimodal Learning from Data-centric PerspectiveCode5
Multimodal Autoregressive Pre-training of Large Vision EncodersCode5
Chinese CLIP: Contrastive Vision-Language Pretraining in ChineseCode5
Open-Vocabulary SAM: Segment and Recognize Twenty-thousand Classes InteractivelyCode5
Scalable Pre-training of Large Autoregressive Image ModelsCode5
A ConvNet for the 2020sCode5
Sequencer: Deep LSTM for Image ClassificationCode5
Efficient Deformable ConvNets: Rethinking Dynamic and Sparse Operator for Vision ApplicationsCode4
Kolmogorov-Arnold TransformerCode4
Detectron2 Object Detection & Manipulating Images using CartoonizationCode4
Architecture-Agnostic Masked Image Modeling -- From ViT back to CNNCode4
InternImage: Exploring Large-Scale Vision Foundation Models with Deformable ConvolutionsCode4
Kolmogorov-Arnold Convolutions: Design Principles and Empirical StudiesCode4
Show:102550
← PrevPage 1 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
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