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 13011325 of 10420 papers

TitleStatusHype
TDAM: Top-Down Attention Module for Contextually Guided Feature Selection in CNNsCode1
ACPL: Anti-curriculum Pseudo-labelling for Semi-supervised Medical Image ClassificationCode1
ML-Decoder: Scalable and Versatile Classification HeadCode1
Domain Prompt Learning for Efficiently Adapting CLIP to Unseen DomainsCode1
PeCo: Perceptual Codebook for BERT Pre-training of Vision TransformersCode1
Sharpness-aware Quantization for Deep Neural NetworksCode1
AutoDC: Automated data-centric processingCode1
Focal and Global Knowledge Distillation for DetectorsCode1
SSR: An Efficient and Robust Framework for Learning with Unknown Label NoiseCode1
Florence: A New Foundation Model for Computer VisionCode1
FedCV: A Federated Learning Framework for Diverse Computer Vision TasksCode1
Semi-Supervised Vision TransformersCode1
Grounded Situation Recognition with TransformersCode1
Swin Transformer V2: Scaling Up Capacity and ResolutionCode1
Benchmarking and scaling of deep learning models for land cover image classificationCode1
Detecting AutoAttack Perturbations in the Frequency DomainCode1
LiT: Zero-Shot Transfer with Locked-image text TuningCode1
iBOT: Image BERT Pre-Training with Online TokenizerCode1
Probabilistic Contrastive Learning for Domain AdaptationCode1
Masked Autoencoders Are Scalable Vision LearnersCode1
Keys to Accurate Feature Extraction Using Residual Spiking Neural NetworksCode1
FILIP: Fine-grained Interactive Language-Image Pre-TrainingCode1
Sliced Recursive TransformerCode1
TAGLETS: A System for Automatic Semi-Supervised Learning with Auxiliary DataCode1
Improved Regularization and Robustness for Fine-tuning in Neural NetworksCode1
Show:102550
← PrevPage 53 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