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

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 8051–8075 of 10420 papers

TitleStatusHype
Deep Active Learning in the Open World—0
Improved Mix-up with KL-Entropy for Learning From Noisy Labels—0
Does Deep Active Learning Work in the Wild?—0
Improved Image Classification with Token Fusion—0
Improved Image Classification with Manifold Neural Networks—0
Rethinking the Zigzag Flattening for Image Reading—0
Rethinking Two Consensuses of the Transferability in Deep Learning—0
Deep Active Ensemble Sampling For Image Classification—0
Rethinking VLMs and LLMs for Image Classification—0
Automatic Discovery and Optimization of Parts for Image Classification—0
Automatic Detection and Image Recognition of Precision Agriculture for Citrus Diseases—0
Improved Fine-Tuning by Better Leveraging Pre-Training Data—0
Improved Few-Shot Visual Classification—0
Retrain or not retrain? -- efficient pruning methods of deep CNN networks—0
Decoupling Feature Extraction and Classification Layers for Calibrated Neural Networks—0
Retrieval-enriched zero-shot image classification in low-resource domains—0
Improved Few-Shot Image Classification Through Multiple-Choice Questions—0
Automatic Dataset Construction (ADC): Sample Collection, Data Curation, and Beyond—0
Improved EATFormer: A Vision Transformer for Medical Image Classification—0
Improved Deep Neural Network Generalization Using m-Sharpness-Aware Minimization—0
Reveal of Vision Transformers Robustness against Adversarial Attacks—0
Improved Conformer-based End-to-End Speech Recognition Using Neural Architecture Search—0
Reversed Active Learning based Atrous DenseNet for Pathological Image Classification—0
Reverse engineering adversarial attacks with fingerprints from adversarial examples—0
All-You-Can-Fit 8-Bit Flexible Floating-Point Format for Accurate and Memory-Efficient Inference of Deep Neural Networks—0
Show:102550
← PrevPage 323 of 417Next →
All datasetsImageNetCIFAR-10CIFAR-100STL-10ObjectNetMNISTSVHNiNaturalist 2018ImageNet ReaLFlowers-102Clothing1Mmini WebVision 1.0

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1CoCa (finetuned)Top 1 Accuracy91—Unverified
2Model soups (BASIC-L)Top 1 Accuracy90.98—Unverified
3Model soups (ViT-G/14)Top 1 Accuracy90.94—Unverified
4DaViT-GTop 1 Accuracy90.4—Unverified
5DaViT-HTop 1 Accuracy90.2—Unverified
6Meta Pseudo Labels (EfficientNet-L2)Top 1 Accuracy90.2—Unverified
7SwinV2-GTop 1 Accuracy90.17—Unverified
8MAWS (ViT-6.5B)Top 1 Accuracy90.1—Unverified
9Florence-CoSwin-HTop 1 Accuracy90.05—Unverified
10Meta Pseudo Labels (EfficientNet-B6-Wide)Top 1 Accuracy90—Unverified